Advisory

PYSEC-2026-75

Also known as: CVE-2024-58340

Summary

The record has no summary.

Details

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.

Severity

High Basis: CVSS v3 score 7.5, vector CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

Dates

Published
2026-01-12 23:15 UTC
Modified
2026-05-20 09:19 UTC

Affected packages and fixes

langchain-exa

PyPI · All systems

Affected

  • introduced 0, fixed 1.0.0a1 (ecosystem)

Fixed versions

1.0.0a1

Fix

  • Fixed version 1.0.0a1
    pip install --upgrade langchain-exa==1.0.0a1

Fix commands are the export's own generic commands. Ojuju never runs them. Check them against your setup first.

Check your own computer: guard packages check

View this record on OSV.dev

Source

Source: PyPA Advisory Database · CC BY 4.0

Sources & licences