fetch-youtube-transcript

Warn

Audited by Snyk on Mar 10, 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 to fetch transcripts from public YouTube URLs using youtube-transcript-api (see "Purpose/Usage" and the execution steps), which are untrusted, user-generated third‑party content that the agent is expected to ingest/save and use for analysis—creating a clear vector for indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 10, 2026, 06:49 AM