Track vulnerabilities like this one.
Sign up free to get alerted when software you use is affected.
9.8
CVE-2026-31020: DocsGPT 0.15.0 lets attackers run code
CVE-2026-31020 · published 2 months ago
Summary
DocsGPT versions up to 0.15 let users add their own prompt text, but the app does not check that text for dangerous content. An attacker could insert special commands that the system will execute, giving them control of the server. Upgrade to a newer DocsGPT release or disable the custom prompt feature and apply any available patches.
Original advisory text
In DocsGPT 0.15.0 and below, the application provides a custom prompt feature that allows users to define prompt content used during chatbot interactions. This functionality renders user-supplied p...
In DocsGPT 0.15.0 and below, the application provides a custom prompt feature that allows users to define prompt content used during chatbot interactions. This functionality renders user-supplied prompt data using Jinja templates without input sanitization or sandboxing. An unauthenticated attacker can inject malicious template expressions, leading to a server-side template injection (SSTI) vulnerability that can be exploited to achieve full remote code execution (RCE).
Internet-facing
3 days
Internal
60 days
- Not known to be exploited
- Can be exploited automatically
- Gives an attacker full control
Severity
9.8
Critical
Type
CWE-94Code Injection
Timeline
Published4 Sep 2026
Updated31 Oct 2026
First seen4 Sep 2026
Track software like this
Free during beta