Browse / AI Framework and Platform Flaws / CVE-2023-46229
LangChain Server Side Request Forgery vulnerability
- Class
- AI Framework and Platform Flaws (filed by a model that read the advisory)
- Technique
- Server-side request forgery
- Affected
- langchain (PyPI)
- CVSS
- CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
- EPSS
- 42.3% chance of exploitation in 30 days
How it works, in short
Crawling in LangChain's recursive URL document loader can be pointed from an external page to internal servers, so the host issues requests it should not. (Our summary, written by a model. The source text is below.)
Details
LangChain before 0.0.317 allows SSRF via document_loaders/recursive_url_loader.py because crawling can proceed from an external server to an internal server.
References
- https://nvd.nist.gov/vuln/detail/CVE-2023-46229
- https://github.com/langchain-ai/langchain/pull/11925
- https://github.com/langchain-ai/langchain/commit/9ecb7240a480720ec9d739b3877a52f76098a2b8
- https://github.com/langchain-ai/langchain
- https://github.com/pypa/advisory-database/tree/main/vulns/langchain/PYSEC-2023-205.yaml
Source: GitHub Advisory Database, used under CC BY 4.0.