youtube-transcript
Warn
Audited by Snyk on Mar 25, 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 scripts (scripts/fetch-transcript.mjs) explicitly fetch and parse transcripts from public YouTube endpoints (watch page, timedtext API, youtubei) and SKILL.md requires the agent to read the saved transcript file and use it as the source for translation/summarization, so untrusted, user-generated YouTube content can directly influence the agent's outputs and actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata