research

Warn

Audited by Snyk on Feb 20, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 1.00). SKILL.md together with modules/web-search-protocol.md and modules/media-collection.md explicitly require using WebSearch/WebFetch to retrieve and validate public URLs, images, and YouTube videos (public/user-generated third‑party content) and to extract facts, timestamps, and media that directly drive content selection, embedding, and downstream agent actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 20, 2026, 04:11 PM