langchain-ai/langchain · Security
LangChain Experimental Eval Injection vulnerability
- GHSA ID
- GHSA-p2qj-r53j-h3xj
- CVE ID
- CVE-2024-46946
- Severity
- critical
- Published
- Updated
- CVSS
- 9.8 · CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
- CVSS v3
- 9.8 · CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
- CVSS v4
- 9.3 · CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
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).
CWEs
- CWE-95 · Improper Neutralization of Directives in Dynamically Evaluated Code ('Eval Injection')
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/releases/tag/langchain-experimental%3D%3D0.3.0 ↗
- https://github.com/advisories/GHSA-p2qj-r53j-h3xj ↗