by Kastro
Paper/Archive/CVE-2026-31020

CVE-2026-31020

mitre — In DocsGPT 0.15.0 and below, the application provides a custom prompt feature that allows users to define prompt content used during chat…

EPSS 1%CVSS 9.8
critical.is priorityof 100
42
CVSS 9.8 (ADP)9.8 / 10 × 3029.4Not in CISA KEV+300.0EPSS percentile 64.0.640 × 2012.8No public exploit+100.0SSVC exploitation: none+100.0
Description · from the CVE record

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).

Affected

ProductAffectedFixed inSource
n/an/a–CNA

Scores by source

CISA ADP9.8CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
CISA ADPSSVCExploitation: none · Automatable: yes · Technical impact: total

References

refarc53.comrefgithub.com/PhDg1410/CVE/tree/main/CVE-2026-31020