Upgrades
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: 0.90). The skill ingests and analyzes untrusted public content—e.g., user-customizable YouTube channels listed in youtube-channels.json (processed via the VideoTranscript tool) and public blogs/GitHub/Discord sources from sources.json—as part of its workflows, exposing the agent to third-party user-generated content.
Audit Metadata