{"id":"CVE-2024-46946","aliases":["GHSA-p2qj-r53j-h3xj","PYSEC-2026-374"],"title":"LangChain Experimental Eval Injection vulnerability","summary":"LangChain Experimental Eval Injection vulnerability","severity":"critical","cvss":9.8,"cvssVector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H","vendor":"langchain-experimental","product":"langchain-experimental","ecosystem":"pip","affected":["langchain-experimental >= 0.1.17, <= 0.3.0"],"published":"2024-09-19","updated":"2026-10-27","sourceUpdated":"2026-10-27T17:00:03.986872162Z","source":"OSV","sourceUrl":"https://osv.dev/vulnerability/GHSA-p2qj-r53j-h3xj","references":[{"url":"https://nvd.nist.gov/vuln/detail/CVE-2024-46946"},{"url":"https://docs.sympy.org/latest/modules/codegen.html"},{"url":"https://gist.github.com/12end/68c0c58d2564ef4141bccd4651480820#file-cve-2024-46946-txt"},{"url":"https://github.com/langchain-ai/langchain"},{"url":"https://github.com/langchain-ai/langchain/releases/tag/langchain-experimental%3D%3D0.3.0"},{"url":"https://github.com/pypa/advisory-database/tree/main/vulns/langchain-experimental/PYSEC-2026-374.yaml"},{"url":"https://pypi.org/project/langchain-experimental"},{"url":"https://github.com/advisories/GHSA-p2qj-r53j-h3xj"}],"tags":["osv","pip","ghsa"],"epss":0.01387,"epssPercentile":0.72097,"cwe":["CWE-95"],"ingestedAt":"2026-10-27T17:33:23.772Z","slug":"CVE-2024-46946","body":"## Overview\n\nlangchain_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).\n\n## Affected packages\n\n- `langchain-experimental >= 0.1.17, <= 0.3.0`\n\n## Remediation\n\nRefer to the advisory for the patched release.","depth":"midnight","depthScore":54,"depthScoreParts":{"impact":53.9,"likelihood":0.3,"exploitation":0,"ransomware":0},"changes":[]}