youtube

Warn

Audited by Snyk on Mar 1, 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.md explicitly instructs fetching and ingesting public YouTube content (e.g., commands with "VIDEO_URL"/"PLAYLIST_URL" and flags like --write-subs, --dump-json to retrieve transcripts/descriptions/metadata), which are untrusted user-generated sources that the agent is expected to read and could materially influence actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 0.70). The skill relies on uvx to automatically fetch and run the latest yt-dlp at runtime (e.g., https://github.com/yt-dlp/yt-dlp), which means remote code is retrieved and executed as a required dependency.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 1, 2026, 06:32 PM