DocsGPT is a GPT-powered chat for documentation. From version 0.15.0 to before version 0.16.0, an attacker accessing both the official DocsGPT website or any local and public deployment, can craft a malicious payload bypassing the "MCP test" behavior to achieve arbitrary remote code execution (RCE). This issue has been patched in version 0.16.0.
Fix
Patch, vendor advisory and mitigation references on NVD 2
- https://github.com/arc53/DocsGPT/security/advisories/GHSA-gcrq-f296-2j74 Exploit, Vendor Advisory
- https://github.com/arc53/DocsGPT/security/advisories/GHSA-gcrq-f296-2j74 Exploit, Vendor Advisory
Every line above is quoted from NVD, CISA, Microsoft, the vendor's own advisory or DISA; nothing is generated.
Change history 1
- First seenCVSS 10.0 · arc53NVD modified 2026-10-26 20:10
Affected (CPE criteria) 1
cpe:2.3:a:arc53:docsgpt:0.15.0:*:*:*:*:*:*:*
References 5
- https://github.com/arc53/DocsGPT/releases/tag/0.16.0 Release Notes
- https://github.com/arc53/DocsGPT/security/advisories/GHSA-gcrq-f296-2j74 Exploit, Vendor Advisory
- https://www.ox.security/blog/mcp-supply-chain-advisory-rce-vulnerabilities-across-the-ai-ecosystem/
- https://www.ox.security/blog/the-mother-of-all-ai-supply-chains-critical-systemic-vulnerability-at-the-core-of-the-mcp/
- https://github.com/arc53/DocsGPT/security/advisories/GHSA-gcrq-f296-2j74 Exploit, Vendor Advisory