audio-extractor

Warn

Audited by Snyk on Mar 6, 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 explicitly runs yt-dlp on arbitrary public URLs (YouTube, SoundCloud, Bandcamp, podcasts/RSS, etc.) as shown in SKILL.md and scripts/extract_audio.py, ingesting untrusted page/metadata (titles, descriptions, playlist fields) into processing and output templates (filenames, metadata embedding), so third‑party content is fetched and can materially influence tool behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 6, 2026, 02:02 PM