Advisoriesby IbisLangChainGHSA-p2qj-r53j-h3xj
LangChain Experimental Eval Injection vulnerability
No fix yet
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 versions
| Package | Affected | Fixed in |
|---|---|---|
| langchain-experimental PyPI | >= 0.1.17, <= 0.3.0 | No fix yet |
Details and references
- CVSS 3.1
- CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
- Severity from
- GitHub (reviewed advisory)
- Weakness
- CWE-95
- Also known as
- CVE-2024-46946, PYSEC-2026-374
- nvd.nist.gov/vuln/detail/CVE-2024-46946
- docs.sympy.org/latest/modules/codegen.html
- gist.github.com/12end/68c0c58d2564ef4141bccd4651480820#file-cve-2024-46946-txt
- github.com/langchain-ai/langchain
- github.com/langchain-ai/langchain/releases/tag/langchain-experimental%3D%3D0.3.0
- github.com/pypa/advisory-database/tree/main/vulns/langchain-experimental/PYSEC-2026-374.yaml
- pypi.org/project/langchain-experimental
More LangChain advisories
All LangChain
@langchain/community SQL Injection vulnerabilityCVE-2024-7042fixed in 0.3.3Langchain Path Traversal vulnerabilityCVE-2024-7774fixed in 0.2.19Langchain SQL Injection vulnerabilityCVE-2024-8309fixed in 0.2.0 +1LangChain pickle deserialization of untrusted dataCVE-2024-5998fixed in 0.2.4langchain-experimental vulnerable to Arbitrary Code ExecutionCVE-2024-21513fixed in 0.0.21langchain_experimental Code Execution via Python REPL accessCVE-2024-38459fixed in 0.0.61