# CVE-2024-58340

LangChain MRKLOutputParser.parse() ReDoS via crafted text.

- Page: https://www.vulneraibility.com/cve/CVE-2024-58340
- CVSS: 8.7
- Known exploited: not in CISA KEV as of our last sync
- EPSS: 0.48% (percentile 42.3)
- CISA SSVC: exploitation poc, automatable yes, technical impact partial (assessed 2026-01-13)
- Weakness: CWE-1333
- Published: 2026-01-12

## Affected versions

- LangChain AI LangChain: affected <= 0.3.1

A version outside these ranges is not a statement that it is unaffected.

## Impact

Denial of service: crafted model output causes heavy CPU usage during parsing, risking service slowdown or outage.

## Action

Patch when possible

## Recommendation

Upgrade to fixed LangChain version when released

## References

- [exploit] https://huntr.com/bounties/e7ece02c-d4bb-4166-8e08-6baf4f8845bb
- [other] https://www.langchain.com/
- [other] https://github.com/langchain-ai/langchain
- [advisory] https://www.vulncheck.com/advisories/langchain-mrkloutputparser-redos

---
Summary, impact and action are written by the vulneraibility.com AI analysis pipeline from the CVE record, NVD, CISA and FIRST data; verify against the references.
