pexo-agent

Warn

Audited by Snyk on Mar 10, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly states the skill "Accepts text, images, video, audio, URLs — anything you have becomes input," which indicates it ingests arbitrary user-supplied/untrusted URLs and uses that content as part of its creative workflow (SKILL.md "How to Use" / "Multimodal"), so third-party page content could influence outputs and downstream actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 10, 2026, 11:39 AM