CVE-2024-46946
9.8
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Summary
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).
Affected Software
| Vendor | Product | Version Range | Status |
|---|---|---|---|
| n/a | n/a | n/a | affected |
Weaknesses
- n/a
ADP Enrichment
CISA ADP Vulnrichment
- SSVC:
- Exploitation: poc
- Automatable: yes
- Technical Impact: total
References
- https://cwe.mitre.org/data/definitions/95.html
- https://github.com/langchain-ai/langchain/releases/tag/langchain-experimental%3D%3D0.3.0
- https://docs.sympy.org/latest/modules/codegen.html
- https://gist.github.com/12end/68c0c58d2564ef4141bccd4651480820#file-cve-2024-46946-txt
Feedback
Was this page helpful?
Glad to hear it! Please tell us how we can improve.
Sorry to hear that. Please tell us how we can improve.