MediumVulnerabilityLLM-specific
CVE-2025-6853: Langchain-Chatchat path traversal in upload_temp_docs
- Source
- NVD(opens in a new tab)
- Identifier
- CVE-2025-6853
- Published
- Record updated
- Affected
- langchain-chatchat <= 0.3.1.3
- Fixed in
- No fixed version was stated when the source was last read.
- Known exploitation
- Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
- EPSS
- 0.6%
Summary
A critical path traversal vulnerability (CWE-22) has been found in chatchat-space Langchain-Chatchat up to version 0.3.1. It affects the upload_temp_docs function, reached through the /knowledge_base/upload_temp_docs endpoint of the Backend component, where manipulating the flag argument leads to path traversal. The flaw can be exploited remotely, and public exploit disclosure means it may be used.
Mitigation
The source does not state a fix yet. Check the original advisory for updates.
Related items
- MediumCVE-2026-121936: easyVoice server-side request forgery through openaiBaseUrl in /api/v1/ttsSimilar attack · NVD/CVE Database
- MediumCVE-2026-118628: MLflow get-artifacts server-side request forgery information disclosureSimilar attack · NVD/CVE Database
- HighCVE-2026-118625: MLflow Tracking Server privilege escalation via get_endpointsSimilar attack · NVD/CVE Database
- InfoWhen trust becomes the payload: Inside the threats, etc quarterly reportSimilar attack · Elastic Security Labs
- MediumCritical Langflow flaws enable authentication bypass and RCESimilar attack · CSO Online