CriticalVulnerabilityLLM-specific

CVE-2026-31020: DocsGPT server-side template injection in custom prompt feature

Source: NVD(opens in a new tab)
Identifier: CVE-2026-31020
Published: September 4, 2026
Record updated: October 9, 2026

Known exploitation: Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
EPSS: 1.0%

Summary

CVE-2026-31020 affects DocsGPT 0.15.0 and below. Its custom prompt feature renders user-supplied prompt content through Jinja templates without input sanitization or sandboxing. An unauthenticated attacker can inject malicious template expressions, causing server-side template injection that can lead to full remote code execution.

Mitigation

The source does not state a fix yet. Check the original advisory for updates.

Details

Scores and exploitation

EPSS: 1.0%Estimated probability that this CVE is exploited in the next 30 days, from the FIRST Exploit Prediction Scoring System. Read on November 4, 2026.
Disclosure date: September 4, 2026

Classification

Attack type: Other
Attack sophistication: Trivial
AI component targeted: Plugin
Impact: Confidentiality,
Integrity,
Availability
Labels: security

How this record was produced

Summaries, mitigations and labels on this page are generated automatically from the source. The linked source is authoritative. The source gives this advisory a description and no title, so the title above is a headline generated from the source text.

Original source: https://nvd.nist.gov/vuln/detail/CVE-2026-31020

First tracked: September 4, 2026 at 02:08 PM ET, from NVD/CVE Database

Classifier: claude-haiku-5-5, prompt v4

Classifier confidence: 90% (self-assessed)

Summary

Mitigation

Related items