---
id: CVE-2026-31020
title: >-
  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
summary: >-
  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…
severity: critical
cvss: 9.8
cvssVector: 'CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H'
cwe:
  - CWE-94
published: '2026-09-04'
updated: '2026-09-08'
sourceUpdated: '2026-09-08T19:42:20.313'
source: NVD
sourceUrl: 'https://nvd.nist.gov/vuln/detail/CVE-2026-31020'
references:
  - url: 'http://arc53.com'
    label: cve@mitre.org
  - url: 'https://github.com/PhDg1410/CVE/tree/main/CVE-2026-31020'
    label: cve@mitre.org
tags:
  - nvd
epss: 0.01038
epssPercentile: 0.6239
ingestedAt: '2026-09-08T20:10:03.167Z'
---

## Overview

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).

## Remediation

Refer to the linked advisories for vendor-supplied fixes and affected version ranges.