youtube-transcript-hardened
Warn
Audited by Snyk on Apr 21, 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's primary workflow (scripts/fetch_transcript.py and the SKILL.md "Workflow" step) directly fetches public, user-generated YouTube transcripts (via youtube_transcript_api) and metadata (via noembed.com) and instructs the agent to read and summarize the returned full_text, so untrusted third‑party content can materially influence subsequent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata