Raw vector
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:XSummary
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 Command and Scripting Interpreter (T1059); ranked in the top 35% 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 map to SA-11 (Developer Testing and Evaluation) and SI-10 (Information Input Validation) — see the control section below for these in your framework.
Deeper analysis AI-assisted summary
Synthesised by an AI model from the NVD description and linked references — a reading aid, not an authoritative source.
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 Data
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
- AI-specific weaknesses CR
- CWE-1426 — Malicious LLM input yields unvalidated output reaching RCE sink
Mapped by Cyber Resilience · not in NVD. Poisoning and extraction cases are routed to MITRE ATLAS instead of a synthetic CWE.- Classification Reason
- Matched keywords: gpt, mcp
Related Threats
MITRE ATT&CK Enterprise Techniques
CVEs Like This One
Affected Assets
Mitigating Controls
Control response
—
—
—
V1.2.3V1.2.5V1.2.8V1.2.9
Mitigating Controls (NIST 800-53 r5) AI
Developer testing and evaluation can discover command-construction flaws before deployment.
Input validation directly stops construction of commands from untrusted data containing special elements.
Secure engineering principles include proper neutralization and safe command construction practices.
Mitigating Controls (NIST CSF 2.0) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→CSF cross-walk (authority under review) — links open the control.
Secure SDLC practices directly require input validation and neutralization that prevent command injection.
Runtime monitoring of software and data can detect anomalous command execution resulting from injection.
Identifying recorded vulnerabilities enables remediation of command-injection flaws before exploitation.
Mitigating Controls (ISO/IEC 27001:2022 Annex A) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→ISO cross-walk (authority under review) — links open the control.
Secure coding standards require proper escaping and parameterization of commands, directly eliminating CWE-77.
Security testing in development catches command-injection vulnerabilities before release.
Secure development life cycle mandates input validation and command construction practices that directly prevent command injection.
Application security requirements explicitly call for controls against injection flaws including command injection.
Secure architecture principles reduce the attack surface but do not prescribe the specific neutralization techniques needed.
Environment separation limits the blast radius of an exploited command injection but does not prevent the flaw itself.