Vulnerability in Langchain
CVE-2024-58340
LangChain versions up to and including 0.3.1 contain a regular expression denial-of-service (ReDoS) vulnerability in the MRKLOutputParser.parse() method (libs/langchain/langchain/agents/mrkl/output_parser.py). The parser applies a backtracking-prone regular expression when extracting tool actions from model output. An attacker who can supply or influence the parsed text (for example via prompt injection in downstream applications that pass LLM output directly into MRKLOutputParser.parse()) can trigger excessive CPU consumption by providing a crafted payload, causing significant parsing delays and a denial-of-service condition.
Vulnerability class: ReDoS (Regular Expression Denial of Service)
Published · last modified .
CVSS v3 metric
CVSS v3 base score 7.5 (High). Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H.
EPSS exploit prediction
EPSS 0.005, 42.0th percentile (scored ); unchanged over 30 days. About EPSS.
Affected products
- Langchain
- Langchain Ai — versions 0
Weakness classification (CWE)
References
- huntr.com/bounties/e7ece02c-d4bb-4166-8e08-6baf4f8845bb (Exploit, technical-description, Third Party Advisory, exploit, Issue Tracking)
- www.langchain.com/ (Product, product)
- github.com/langchain-ai/langchain (Product, product)
- www.vulncheck.com/advisories/langchain-mrkloutputparser-redos (Third Party Advisory, third-party-advisory)