CRITICAL 9.8 PyPI
LangChain Experimental Eval Injection vulnerability
GHSA-p2qj-r53j-h3xj · CVE-2024-46946
Published · Modified
Description
langchain_experimental (aka LangChain Experimental) 0.1.17 through 0.3.0 for LangChain allows attackers to execute arbitrary code through sympy.sympify (which uses eval) in LLMSymbolicMathChain. LLMSymbolicMathChain was introduced in fcccde406dd9e9b05fc9babcbeb9ff527b0ec0c6 (2023-10-05).
References
- ADVISORY https://nvd.nist.gov/vuln/detail/CVE-2024-46946
- WEB https://docs.sympy.org/latest/modules/codegen.html
- WEB https://gist.github.com/12end/68c0c58d2564ef4141bccd4651480820#file-cve-2024-46946-txt
- PACKAGE https://github.com/langchain-ai/langchain
- WEB https://github.com/langchain-ai/langchain/releases/tag/langchain-experimental%3D%3D0.3.0
Ready to move
Start Securing
Free, no credit card | First findings in minutes