youtube-verdict
Warn
Audited by Snyk on May 8, 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). The skill explicitly fetches transcripts and metadata from public YouTube URLs (Step 2: running "python3 scripts/fetch.py --cache") and then ingests and processes those untrusted, user-provided transcripts in Pass 1/2/3 to drive LLM decisions and tool behavior, so third-party content could inject instructions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata