CVE-2026-48039 (GCVE-0-2026-48039)

Vulnerability from cvelistv5 – Published: 2026-08-07 19:29 – Updated: 2026-08-07 19:42
VLAI
Title
Meta Ads MCP: Unauthenticated HTTP MCP Tool Execution Leaks Operator Meta Access Token
Summary
Meta Ads MCP is a Model Context Protocol (MCP) server that lets AI assistants run Meta Ads. Prior to version 1.0.109, `AuthInjectionMiddleware.dispatch()` at `http_auth_integration.py:272` unconditionally forwards unauthenticated Streamable HTTP requests to downstream MCP tool handlers without issuing a `401` response, allowing any network-reachable caller to invoke MCP tools without authentication. When no per-request credential is present, tool handlers fall back to the `META_ACCESS_TOKEN` environment variable, and when the downstream Meta Graph API call fails, `api.py:263–269` serialises the raw `httpx` request URL—including the operator's `access_token` as a query parameter—into the JSON-RPC response body, delivering the credential to the unauthenticated caller. Version 1.0.109 fixes the issue.
Severity
9.1 (Critical)
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:N
SSVC
Exploitation: poc Automatable: yes Technical Impact: total
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-08-07 19:41 UTC
CWE
  • CWE-287 - Improper Authentication
Assigner
References
Impacted products
Vendor Product Version
pipeboard-co meta-ads-mcp Affected: < 1.0.109
Create a notification for this product.
Show details on NVD website
To clipboard 

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-48039",
                "options": [
                  {
                    "Exploitation": "poc"
                  },
                  {
                    "Automatable": "yes"
                  },
                  {
                    "Technical Impact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-08-07T19:41:49.858751Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-08-07T19:42:00.728Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "references": [
          {
            "tags": [
              "exploit"
            ],
            "url": "https://github.com/pipeboard-co/meta-ads-mcp/security/advisories/GHSA-9gw6-46qc-99vr"
          }
        ],
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "meta-ads-mcp",
          "vendor": "pipeboard-co",
          "versions": [
            {
              "status": "affected",
              "version": "\u003c 1.0.109"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "Meta Ads MCP is a Model Context Protocol (MCP) server that lets AI assistants run Meta Ads. Prior to version 1.0.109, `AuthInjectionMiddleware.dispatch()` at `http_auth_integration.py:272` unconditionally forwards unauthenticated Streamable HTTP requests to downstream MCP tool handlers without issuing a `401` response, allowing any network-reachable caller to invoke MCP tools without authentication. When no per-request credential is present, tool handlers fall back to the `META_ACCESS_TOKEN` environment variable, and when the downstream Meta Graph API call fails, `api.py:263\u2013269` serialises the raw `httpx` request URL\u2014including the operator\u0027s `access_token` as a query parameter\u2014into the JSON-RPC response body, delivering the credential to the unauthenticated caller. Version 1.0.109 fixes the issue."
        }
      ],
      "metrics": [
        {
          "cvssV3_1": {
            "attackComplexity": "LOW",
            "attackVector": "NETWORK",
            "availabilityImpact": "NONE",
            "baseScore": 9.1,
            "baseSeverity": "CRITICAL",
            "confidentialityImpact": "HIGH",
            "integrityImpact": "HIGH",
            "privilegesRequired": "NONE",
            "scope": "UNCHANGED",
            "userInteraction": "NONE",
            "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:N",
            "version": "3.1"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-287",
              "description": "CWE-287: Improper Authentication",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-08-07T19:29:39.875Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/pipeboard-co/meta-ads-mcp/security/advisories/GHSA-9gw6-46qc-99vr",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/pipeboard-co/meta-ads-mcp/security/advisories/GHSA-9gw6-46qc-99vr"
        },
        {
          "name": "https://github.com/pipeboard-co/meta-ads-mcp/releases/tag/1.0.109",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/pipeboard-co/meta-ads-mcp/releases/tag/1.0.109"
        },
        {
          "name": "https://github.com/pypa/advisory-database/tree/main/vulns/meta-ads-mcp/PYSEC-2026-413.yaml",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/pypa/advisory-database/tree/main/vulns/meta-ads-mcp/PYSEC-2026-413.yaml"
        }
      ],
      "source": {
        "advisory": "GHSA-9gw6-46qc-99vr",
        "discovery": "UNKNOWN"
      },
      "title": "Meta Ads MCP: Unauthenticated HTTP MCP Tool Execution Leaks Operator Meta Access Token"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2026-48039",
    "datePublished": "2026-08-07T19:29:39.875Z",
    "dateReserved": "2026-05-20T18:15:53.578Z",
    "dateUpdated": "2026-08-07T19:42:00.728Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2",
  "vulnerability-lookup:meta": {
    "epss": {
      "cve": "CVE-2026-48039",
      "date": "2026-08-12",
      "epss": "0.00344",
      "percentile": "0.27211"
    },
    "nvd": "{\"cve\":{\"id\":\"CVE-2026-48039\",\"sourceIdentifier\":\"security-advisories@github.com\",\"published\":\"2026-08-07T20:16:51.723\",\"lastModified\":\"2026-08-07T20:16:51.723\",\"vulnStatus\":\"Received\",\"cveTags\":[],\"descriptions\":[{\"lang\":\"en\",\"value\":\"Meta Ads MCP is a Model Context Protocol (MCP) server that lets AI assistants run Meta Ads. Prior to version 1.0.109, `AuthInjectionMiddleware.dispatch()` at `http_auth_integration.py:272` unconditionally forwards unauthenticated Streamable HTTP requests to downstream MCP tool handlers without issuing a `401` response, allowing any network-reachable caller to invoke MCP tools without authentication. When no per-request credential is present, tool handlers fall back to the `META_ACCESS_TOKEN` environment variable, and when the downstream Meta Graph API call fails, `api.py:263\u2013269` serialises the raw `httpx` request URL\u2014including the operator\u0027s `access_token` as a query parameter\u2014into the JSON-RPC response body, delivering the credential to the unauthenticated caller. Version 1.0.109 fixes the issue.\"}],\"affected\":[{\"source\":\"security-advisories@github.com\",\"affectedData\":[{\"vendor\":\"pipeboard-co\",\"product\":\"meta-ads-mcp\",\"versions\":[{\"version\":\"\u003c 1.0.109\",\"status\":\"affected\"}]}]}],\"metrics\":{\"cvssMetricV31\":[{\"source\":\"security-advisories@github.com\",\"type\":\"Secondary\",\"cvssData\":{\"version\":\"3.1\",\"vectorString\":\"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:N\",\"baseScore\":9.1,\"baseSeverity\":\"CRITICAL\",\"attackVector\":\"NETWORK\",\"attackComplexity\":\"LOW\",\"privilegesRequired\":\"NONE\",\"userInteraction\":\"NONE\",\"scope\":\"UNCHANGED\",\"confidentialityImpact\":\"HIGH\",\"integrityImpact\":\"HIGH\",\"availabilityImpact\":\"NONE\"},\"exploitabilityScore\":3.9,\"impactScore\":5.2}],\"ssvcV203\":[{\"source\":\"134c704f-9b21-4f2e-91b3-4a467353bcc0\",\"ssvcData\":{\"timestamp\":\"2026-08-07T19:41:49.858751Z\",\"id\":\"CVE-2026-48039\",\"options\":[{\"exploitation\":\"poc\"},{\"automatable\":\"yes\"},{\"technicalImpact\":\"total\"}],\"role\":\"CISA Coordinator\",\"version\":\"2.0.3\"}}]},\"weaknesses\":[{\"source\":\"security-advisories@github.com\",\"type\":\"Primary\",\"description\":[{\"lang\":\"en\",\"value\":\"CWE-287\"}]}],\"references\":[{\"url\":\"https://github.com/pipeboard-co/meta-ads-mcp/releases/tag/1.0.109\",\"source\":\"security-advisories@github.com\"},{\"url\":\"https://github.com/pipeboard-co/meta-ads-mcp/security/advisories/GHSA-9gw6-46qc-99vr\",\"source\":\"security-advisories@github.com\"},{\"url\":\"https://github.com/pypa/advisory-database/tree/main/vulns/meta-ads-mcp/PYSEC-2026-413.yaml\",\"source\":\"security-advisories@github.com\"},{\"url\":\"https://github.com/pipeboard-co/meta-ads-mcp/security/advisories/GHSA-9gw6-46qc-99vr\",\"source\":\"134c704f-9b21-4f2e-91b3-4a467353bcc0\"}]}}",
    "vulnrichment": {
      "containers": "{\"adp\": [{\"title\": \"CISA ADP Vulnrichment\", \"metrics\": [{\"other\": {\"type\": \"ssvc\", \"content\": {\"id\": \"CVE-2026-48039\", \"role\": \"CISA Coordinator\", \"options\": [{\"Exploitation\": \"poc\"}, {\"Automatable\": \"yes\"}, {\"Technical Impact\": \"total\"}], \"version\": \"2.0.3\", \"timestamp\": \"2026-08-07T19:41:49.858751Z\"}}}], \"references\": [{\"url\": \"https://github.com/pipeboard-co/meta-ads-mcp/security/advisories/GHSA-9gw6-46qc-99vr\", \"tags\": [\"exploit\"]}], \"providerMetadata\": {\"orgId\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"shortName\": \"CISA-ADP\", \"dateUpdated\": \"2026-08-07T19:41:15.339Z\"}}], \"cna\": {\"title\": \"Meta Ads MCP: Unauthenticated HTTP MCP Tool Execution Leaks Operator Meta Access Token\", \"source\": {\"advisory\": \"GHSA-9gw6-46qc-99vr\", \"discovery\": \"UNKNOWN\"}, \"metrics\": [{\"cvssV3_1\": {\"scope\": \"UNCHANGED\", \"version\": \"3.1\", \"baseScore\": 9.1, \"attackVector\": \"NETWORK\", \"baseSeverity\": \"CRITICAL\", \"vectorString\": \"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:N\", \"integrityImpact\": \"HIGH\", \"userInteraction\": \"NONE\", \"attackComplexity\": \"LOW\", \"availabilityImpact\": \"NONE\", \"privilegesRequired\": \"NONE\", \"confidentialityImpact\": \"HIGH\"}}], \"affected\": [{\"vendor\": \"pipeboard-co\", \"product\": \"meta-ads-mcp\", \"versions\": [{\"status\": \"affected\", \"version\": \"\u003c 1.0.109\"}]}], \"references\": [{\"url\": \"https://github.com/pipeboard-co/meta-ads-mcp/security/advisories/GHSA-9gw6-46qc-99vr\", \"name\": \"https://github.com/pipeboard-co/meta-ads-mcp/security/advisories/GHSA-9gw6-46qc-99vr\", \"tags\": [\"x_refsource_CONFIRM\"]}, {\"url\": \"https://github.com/pipeboard-co/meta-ads-mcp/releases/tag/1.0.109\", \"name\": \"https://github.com/pipeboard-co/meta-ads-mcp/releases/tag/1.0.109\", \"tags\": [\"x_refsource_MISC\"]}, {\"url\": \"https://github.com/pypa/advisory-database/tree/main/vulns/meta-ads-mcp/PYSEC-2026-413.yaml\", \"name\": \"https://github.com/pypa/advisory-database/tree/main/vulns/meta-ads-mcp/PYSEC-2026-413.yaml\", \"tags\": [\"x_refsource_MISC\"]}], \"descriptions\": [{\"lang\": \"en\", \"value\": \"Meta Ads MCP is a Model Context Protocol (MCP) server that lets AI assistants run Meta Ads. Prior to version 1.0.109, `AuthInjectionMiddleware.dispatch()` at `http_auth_integration.py:272` unconditionally forwards unauthenticated Streamable HTTP requests to downstream MCP tool handlers without issuing a `401` response, allowing any network-reachable caller to invoke MCP tools without authentication. When no per-request credential is present, tool handlers fall back to the `META_ACCESS_TOKEN` environment variable, and when the downstream Meta Graph API call fails, `api.py:263\\u2013269` serialises the raw `httpx` request URL\\u2014including the operator\u0027s `access_token` as a query parameter\\u2014into the JSON-RPC response body, delivering the credential to the unauthenticated caller. Version 1.0.109 fixes the issue.\"}], \"problemTypes\": [{\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-287\", \"description\": \"CWE-287: Improper Authentication\"}]}], \"providerMetadata\": {\"orgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"shortName\": \"GitHub_M\", \"dateUpdated\": \"2026-08-07T19:29:39.875Z\"}}}",
      "cveMetadata": "{\"cveId\": \"CVE-2026-48039\", \"state\": \"PUBLISHED\", \"dateUpdated\": \"2026-08-07T19:42:00.728Z\", \"dateReserved\": \"2026-05-20T18:15:53.578Z\", \"assignerOrgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"datePublished\": \"2026-08-07T19:29:39.875Z\", \"assignerShortName\": \"GitHub_M\"}",
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }
  }
}



Log in or create an account to share your comment.




Tags
Taxonomy of the tags.





Forecast uses a logistic model when the trend is rising, or an exponential decay model when the trend is falling. Fitted via linearized least squares.

Sightings

Author Source Type Date Other

Nomenclature

  • Seen: The vulnerability was mentioned, discussed, or observed by the user.
  • Confirmed: The vulnerability has been validated from an analyst's perspective.
  • Published Proof of Concept: A public proof of concept is available for this vulnerability.
  • Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
  • Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
  • Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
  • Not confirmed: The user expressed doubt about the validity of the vulnerability.
  • Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.


Detection rules are retrieved from Rulezet.