yt-brief
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: 0.80). The SKILL.md explicitly instructs the agent in "Step 1: Research the Topic" to use WebSearch ("Use WebSearch if needed") and to review external announcements (e.g., "Anthropic's announcement blog post" in examples), meaning the agent will fetch and interpret open/public third‑party content that can influence briefing decisions and next actions.
Audit Metadata