youtube-transcript
Warn
Audited by Snyk on Feb 28, 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 downloads transcripts from YouTube (Step 3: "Download Transcript") and then reads/parses those user-generated auto/manual captions to identify visual-reference timestamps (Step 4), allowing arbitrary third-party content to influence frame extraction and subsequent analysis.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.80). The skill downloads transcripts from the user-supplied YouTube URL (e.g., https://www.youtube.com/watch?v=... or https://youtu.be/...) at runtime and injects that fetched transcript content into the agent's analysis/context, which can directly influence prompts and behavior.
Audit Metadata