customgpt

Warn

Audited by Snyk on Mar 13, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.90). This skill's SKILL.md explicitly allows adding and indexing arbitrary sitemap URLs or file URLs as knowledge sources (see "Create Agent" / "Create Source") and exposes actions like "List Pages" and "List Sources" so the agent will read and act on untrusted public web pages and documents via the CustomGPT API.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 13, 2026, 10:44 AM
Issues
1