LangChain Experimental Eval Injection vulnerability
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
Click a technology to see all vulnerabilities affecting it.
| Platform | Package | Vulnerable versions | Fixed in |
|---|---|---|---|
| Python (PyPI) | langchain-experimental | >= 0.1.17, <= 0.3.0 | no fix |
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
- https://github.com/langchain-ai/langchain/releases/tag/langchain-experimental%3D%3D0.3.0
- https://pypi.org/project/langchain-experimental
- https://github.com/advisories/GHSA-p2qj-r53j-h3xj
- CVSS vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H- Weakness (CWE)
CWE-95- Platform
- Python (PyPI)
- Package
langchain-experimental- Disclosed
- 19.09.2024
- Updated
- 11.10.2026 12:20
Sources and licenses
OSV / GitHub Advisory Database - GHSA-p2qj-r53j-h3xj - CC BY 4.0
OSV / GitHub Advisory Database - PYSEC-2026-374 - PyPA Advisory Database; CC BY 4.0
Vulnerability history: langchain-experimental
All published vulnerabilities of this package (Python (PyPI)), newest first. Shows whether this is a one-off slip or a package that needs watching.
- Total entries
- 5
- First → latest
- 10.2023 09.2024
- Without a fix
- 1
- Exploited in attacks
- 0
Severity breakdown
- Critical 4
- High 1
Disclosures per year
- 2023: 1
- 2024: 4
- 2025: 0
- 2026: 0
-
LangChain Experimental Eval Injection vulnerability this entry
Know which vulnerabilities affect your application
With the DockRay integration and software inventory enabled, DockRay checks reported component versions against known vulnerabilities and notifies you about confirmed matches. Coverage depends on the supported technology and available advisory data.