story-explanation
Warn
Audited by Snyk on Feb 16, 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). This skill explicitly fetches and ingests open web content (Step 1: Content Extraction — e.g., fabric -y "YOUTUBE_URL" and WebFetch(url, "Extract full content of this article")) and then reads and analyzes that raw third-party/public content as part of its workflow, exposing the agent to untrusted/user-generated sources.
Audit Metadata