Critical severityNVD Advisory· Published Sep 19, 2024· Updated Sep 19, 2024

CVE-2024-46946

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).

AI Insight

LLM-synthesized narrative grounded in this CVE's description and references.

Affected packages

Versions sourced from the GitHub Security Advisory.

Package	Affected versions	Patched versions
langchain-experimentalPyPI	>= 0.1.17, <= 0.3.0	—

Affected products

Langchain AI/langchain_experimentalcpe-rescue
ghsa-coords
pkg:pypi/langchain-experimental
Range: >= 0.1.17, <= 0.3.0

Patches

Vulnerability mechanics

References

github.com/advisories/GHSA-p2qj-r53j-h3xjghsaADVISORY
nvd.nist.gov/vuln/detail/CVE-2024-46946ghsaADVISORY
docs.sympy.org/latest/modules/codegen.htmlghsaWEB
gist.github.com/12end/68c0c58d2564ef4141bccd4651480820ghsaWEB
github.com/langchain-ai/langchain/releases/tag/langchain-experimental%3D%3D0.3.0ghsaWEB
cwe.mitre.org/data/definitions/95.htmlmitre

News mentions

No linked articles in our index yet.

cvss	0.585
epss	0.001
exploit	0.000
kev	0.000
patch	-0.070
ransomware	0.000