GHSA-PW95-88FG-3J6F
Vulnerability from github – Published: 2025-05-05 20:40 – Updated: 2025-05-05 22:07Summary
A LLM application leveraging XMLToolMessage class may be exposed to untrusted XML input that could result in DoS and/or exposing local files with sensitive information.
Details
XMLToolMessage uses lxml without safeguards:
https://github.com/langroid/langroid/blob/df6227e6c079ec22bb2768498423148d6685acff/langroid/agent/xml_tool_message.py#L51-L52
lxml is vulnerable to quadratic blowup attacks and processes external entity declarations for local files by default.
Check here: https://pypi.org/project/defusedxml/#python-xml-libraries
PoC
A typical Quadratic blowup XML payload looks like this:
<!DOCTYPE bomb [
<!ENTITY a "aaaaaaaaaa">
<!ENTITY b "&a;&a;&a;&a;&a;&a;&a;&a;&a;&a;">
<!ENTITY c "&b;&b;&b;&b;&b;&b;&b;&b;&b;&b;">
]>
<bomb>&c;</bomb>
Here, &a; expands to 10 characters, &b; expands to 100, and &c; expands to 1000, causing exponential memory usage and potentially crashing the application.
Fix
Langroid 0.53.4 initializes XMLParser with flags to prevent XML External Entity (XXE), billion laughs, and external DTD attacks by disabling entity resolution, DTD loading, and network access.
https://github.com/langroid/langroid/commit/36e7e7db4dd1636de225c2c66c84052b1e9ac3c3
{
"affected": [
{
"package": {
"ecosystem": "PyPI",
"name": "langroid"
},
"ranges": [
{
"events": [
{
"introduced": "0"
},
{
"fixed": "0.53.4"
}
],
"type": "ECOSYSTEM"
}
]
}
],
"aliases": [
"CVE-2025-46726"
],
"database_specific": {
"cwe_ids": [
"CWE-611"
],
"github_reviewed": true,
"github_reviewed_at": "2025-05-05T20:40:44Z",
"nvd_published_at": "2025-05-05T20:15:21Z",
"severity": "HIGH"
},
"details": "### Summary\nA LLM application leveraging `XMLToolMessage` class may be exposed to untrusted XML input that could result in DoS and/or exposing local files with sensitive information.\n\n### Details\n`XMLToolMessage` uses `lxml` without safeguards:\nhttps://github.com/langroid/langroid/blob/df6227e6c079ec22bb2768498423148d6685acff/langroid/agent/xml_tool_message.py#L51-L52\n`lxml` is vulnerable to quadratic blowup attacks and processes external entity declarations for local files by default. \nCheck here: https://pypi.org/project/defusedxml/#python-xml-libraries\n\n### PoC\nA typical Quadratic blowup XML payload looks like this:\n```xml\n\u003c!DOCTYPE bomb [\n\u003c!ENTITY a \"aaaaaaaaaa\"\u003e\n\u003c!ENTITY b \"\u0026a;\u0026a;\u0026a;\u0026a;\u0026a;\u0026a;\u0026a;\u0026a;\u0026a;\u0026a;\"\u003e\n\u003c!ENTITY c \"\u0026b;\u0026b;\u0026b;\u0026b;\u0026b;\u0026b;\u0026b;\u0026b;\u0026b;\u0026b;\"\u003e\n]\u003e\n\u003cbomb\u003e\u0026c;\u003c/bomb\u003e\n```\nHere, \u0026a; expands to 10 characters, \u0026b; expands to 100, and \u0026c; expands to 1000, causing exponential memory usage and potentially crashing the application.\n \n### Fix\nLangroid 0.53.4 initializes `XMLParser` with flags to prevent XML External Entity (XXE), billion laughs, and external DTD attacks by disabling entity resolution, DTD loading, and network access.\nhttps://github.com/langroid/langroid/commit/36e7e7db4dd1636de225c2c66c84052b1e9ac3c3",
"id": "GHSA-pw95-88fg-3j6f",
"modified": "2025-05-05T22:07:30Z",
"published": "2025-05-05T20:40:44Z",
"references": [
{
"type": "WEB",
"url": "https://github.com/langroid/langroid/security/advisories/GHSA-pw95-88fg-3j6f"
},
{
"type": "ADVISORY",
"url": "https://nvd.nist.gov/vuln/detail/CVE-2025-46726"
},
{
"type": "WEB",
"url": "https://github.com/langroid/langroid/commit/36e7e7db4dd1636de225c2c66c84052b1e9ac3c3"
},
{
"type": "PACKAGE",
"url": "https://github.com/langroid/langroid"
},
{
"type": "WEB",
"url": "https://github.com/langroid/langroid/blob/df6227e6c079ec22bb2768498423148d6685acff/langroid/agent/xml_tool_message.py#L51-L52"
}
],
"schema_version": "1.4.0",
"severity": [
{
"score": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:N/VA:H/SC:N/SI:N/SA:N/E:P",
"type": "CVSS_V4"
}
],
"summary": "Langroid Allows XXE Injection via XMLToolMessage"
}
Sightings
| Author | Source | Type | Date |
|---|
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.