CVE-2024-58340: LangChain ReDoS in MRKLOutputParser.parse() via crafted model output

Summary

LangChain versions up to and including 0.3.1 contain a regular expression denial-of-service (ReDoS) flaw in the MRKLOutputParser.parse() method (libs/langchain/langchain/agents/mrkl/output_parser.py). The parser runs a backtracking-prone regular expression when extracting tool actions from model output, so an attacker who can supply or influence the parsed text, for example through prompt injection in downstream applications that pass LLM output directly into the parser, can cause excessive CPU consumption and significant parsing delays.

Mitigation

The source does not state a fix yet. Check the original advisory for updates.

Related items

• MediumGHSA-8prr-f582-jqq3: LangGraph CLI prints the registry push token in `langgraph deploy --verbose` outputSame vendor · GitHub Advisory Database
• HighGHSA-4hm6-w6qq-w73v: LangGraph JavaScript custom authentication may permit cross-user Store accessSame vendor · GitHub Advisory Database
• MediumGHSA-3fx2-cqw9-xr3c: LangGraph: Unencoded identifiers in LangGraph SDK v3 streaming can redirect authenticated GET requestsSame vendor · GitHub Advisory Database
• MediumGHSA-6hmw-9432-67qq: LangGraph: Namespace labels containing `.` reach other namespaces in Postgres and SQLite storesSame vendor · GitHub Advisory Database
• MediumCVE-2026-108575: BerriAI LiteLLM improper authorization in secret resolution via api_keySame vendor · NVD/CVE Database