Browse / Improper Output Handling / CVE-2024-46946
LangChain Experimental Eval Injection vulnerability
- Class
- Improper Output Handling (filed by a model that read the advisory)
- Technique
- Code and command execution
- Affected
- langchain-experimental (PyPI)
- CVSS
- CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
- EPSS
- 1.4% chance of exploitation in 30 days
How it works, in short
The symbolic math chain passes model-generated expressions to sympify, which calls eval, so injected text in the output executes as code. (Our summary, written by a model. The source text is below.)
Details
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
- https://nvd.nist.gov/vuln/detail/CVE-2024-46946
- https://docs.sympy.org/latest/modules/codegen.html
- https://gist.github.com/12end/68c0c58d2564ef4141bccd4651480820#file-cve-2024-46946-txt
- https://github.com/langchain-ai/langchain
- https://github.com/langchain-ai/langchain/releases/tag/langchain-experimental%3D%3D0.3.0
- https://github.com/pypa/advisory-database/tree/main/vulns/langchain-experimental/PYSEC-2026-374.yaml
- https://pypi.org/project/langchain-experimental
Source: GitHub Advisory Database, used under CC BY 4.0.