Description
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.
Affected products
arc53: docsgpt
References5
- github.com/arc53/DocsGPT/security/advisories/GHSA-gcrq-f296-2j74 ExploitVendor Advisory
- github.com/arc53/DocsGPT/security/advisories/GHSA-gcrq-f296-2j74 ExploitVendor Advisory
- github.com/arc53/DocsGPT/releases/tag/0.16.0 Release Notes
- www.ox.security/blog/mcp-supply-chain-advisory-rce-vulnerabilit…
- www.ox.security/blog/the-mother-of-all-ai-supply-chains-critica…
Metrics
- CVSS 3.1
-
9.8
CRITICAL
Score source: NVD
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H - CVSS 4.0
-
10.0
CRITICAL
Score source: CNA
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X - EPSS — exploit probability
- 1% percentile: 68 · as of 13 November 2026
- CWE
- CWE-77
Could this be exploited in your environment?
A patch closes the known hole. A penetration test shows what an attacker can still reach — with proof.