deep-research
Warn
Audited by Snyk on Feb 27, 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's Phase 2 "Parallel Research" and Source Selection explicitly instruct research agents to execute web searches (mcp__exa__web_search_exa, WebSearch fallback) and use yt-transcribe, meaning the agents fetch and read public web/YouTube content as required inputs that will directly influence synthesized findings and next actions.
Audit Metadata