CVE-2025-46726
Langroid Allows XXE Injection via XMLToolMessage
Sévérité par source
Le label propre à Trivy est CRITICAL. Critique selon NVD. Plus basse selon GHSA (élevée).
Description
Langroid is a framework for building large-language-model-powered applications. Prior to version 0.53.4, 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. Version 0.53.4 fixes the issue.
Paquets affectés et versions corrigées
| Source | Paquet | Corrigé en |
|---|---|---|
| pip::GitHub Security Advisory pip | langroid | 0.53.4 |
Références
- https://github.com/langroid/langroid
- https://github.com/langroid/langroid/blob/df6227e6c079ec22bb2768498423148d6685acff/langroid/agent/xml_tool_message.py#L51-L52
- https://github.com/langroid/langroid/commit/36e7e7db4dd1636de225c2c66c84052b1e9ac3c3
- https://github.com/langroid/langroid/security/advisories/GHSA-pw95-88fg-3j6f
- https://nvd.nist.gov/vuln/detail/CVE-2025-46726