VulnerabilityAnalyzed

CVE-2024-46946

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.

CRITICAL 9.8EPSS 1.39%

Does this matter?

High impact if exploited, but EPSS currently rates exploitation as unlikely (1.39%). Schedule it in the normal patch cycle and watch for a rise in EPSS or a public exploit.

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).

CVSS 3.1: 9.8 CRITICALCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
EPSS: 1.39% probability · 71th percentile
CISA KEV: Not listed
Weakness: CWE-20
Affected: langchain/langchain-experimental
Source: cve@mitre.org

References

https://cwe.mitre.org/data/definitions/95.htmlNot Applicable
https://docs.sympy.org/latest/modules/codegen.htmlTechnical Description
https://gist.github.com/12end/68c0c58d2564ef4141bccd4651480820#file-cve-2024-46946-txtExploit, Third Party Advisory
https://github.com/langchain-ai/langchain/releases/tag/langchain-experimental%3D%3D0.3.0Release Notes

Source: NVD record, EPSS from FIRST.org, KEV from CISA. Refreshed daily.