{"action":"Upgrade langchain to 0.0.132 or later.","affected":[{"fixed":"0.0.132","introduced":"0"}],"component":"langchain","cve_ids":["CVE-2023-29374"],"ecosystem":"PyPI","epss":0.39653,"exploited":false,"fixed_versions":["0.0.132"],"ghsa_id":"GHSA-fprp-p869-w6q2","id":"tcs_01M5KGJQET9H4Y0HCT30YGE95B","modified_at":"2026-06-10T17:01:57.057107444Z","published_at":"2023-04-05T02:15:00Z","references":["https://osv.dev/vulnerability/PYSEC-2023-18","https://twitter.com/rharang/status/1641899743608463365/photo/1","https://github.com/hwchase17/langchain/pull/1119","https://github.com/hwchase17/langchain/issues/814","https://github.com/hwchase17/langchain/issues/1026","https://github.com/advisories/GHSA-fprp-p869-w6q2"],"severity":{"label":"unknown"},"sources":[{"source":"osv","source_id":"PYSEC-2023-18","url":"https://osv.dev/vulnerability/PYSEC-2023-18"}],"summary":"In LangChain through 0.0.131, the LLMMathChain chain allows prompt injection attacks that can execute arbitrary code via the Python exec method."}