CVE-2026-26015
Published: 29 April 2026
Summary
CVE-2026-26015 is a critical-severity Command Injection (CWE-77) vulnerability in Arc53 Docsgpt. Its CVSS base score is 10.0 (Critical).
Operationally, exploitation aligns with the MITRE ATT&CK technique Exploit Public-Facing Application (T1190); ranked in the top 36.5% of CVEs by exploit likelihood; it is not currently listed in the CISA KEV catalog; a public proof-of-concept is referenced.
This vulnerability is AI-related — categorised as LLM Application Platforms; in the Protocol-Specific Risks risk domain.
The strongest mitigations our analysis identified are NIST 800-53 SC-14 (Public Access Protections) and SI-10 (Information Input Validation).
Deeper analysis
CVE-2026-26015 is a critical remote code execution (RCE) vulnerability in DocsGPT, an open-source GPT-powered chat application for documentation. It affects versions from 0.15.0 up to but not including 0.16.0, impacting both the official DocsGPT website and any local or public deployments of the software. The flaw stems from CWE-77 (command injection), where an attacker can craft a malicious payload that bypasses the "MCP test" behavior, enabling arbitrary code execution on the server. The vulnerability carries a CVSS v3.1 base score of 9.8 (AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H), highlighting its severity due to no authentication or user interaction requirements.
Any unauthenticated attacker with network access to a vulnerable DocsGPT instance can exploit this issue by sending a specially crafted payload through the chat interface or accessible endpoints. Successful exploitation grants full RCE, allowing the attacker to execute arbitrary commands on the host system, potentially leading to complete server compromise, data exfiltration, lateral movement, or persistence in the environment.
The DocsGPT project has addressed this vulnerability in version 0.16.0, as detailed in the official release notes and GitHub security advisory GHSA-gcrq-f296-2j74. Security practitioners should immediately upgrade to version 0.16.0 or later for all deployments, verify patch application, and review access logs for suspicious payloads around the publication date of 2026-04-29.
OWASP Top 10 for Web (2025)
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2026-26258
Vulnerability details
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…
more
arbitrary remote code execution (RCE). This issue has been patched in version 0.16.0.
- CWE(s)
AI Security AnalysisAI
- AI Category
- LLM Application Platforms
- Risk Domain
- Protocol-Specific Risks
- OWASP Top 10 for LLMs 2025
- None mapped
- Classification Reason
- Matched keywords: gpt, mcp
Related Threats
MITRE ATT&CK Enterprise TechniquesAI
Why these techniques?
CVE-2026-26015 enables unauthenticated remote code execution via command injection in the public-facing DocsGPT web chat application, directly facilitating T1190: Exploit Public-Facing Application.
CVEs Like This One
Affected Assets
Mitigating Controls
Mitigating Controls (NIST 800-53 r5) AI
Directly validates and sanitizes user inputs to the chat interface, preventing command injection payloads from bypassing the MCP test and achieving RCE.
Ensures timely identification, testing, and installation of software patches, such as the fix in DocsGPT version 0.16.0, to remediate the command injection flaw.
Protects publicly accessible interfaces like the DocsGPT chat from unauthenticated attackers coercing the system into unsafe operations such as arbitrary RCE.