audio-extraction

Pass

Audited by Gen Agent Trust Hub on Aug 4, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes subprocess.run and shell scripts to execute ffmpeg, ffprobe, and yt-dlp for media processing. The Python code correctly uses list-based argument passing, which is a security best practice to prevent shell injection vulnerabilities.
  • [EXTERNAL_DOWNLOADS]: The skill automates downloading media from external URLs and RSS feeds. It recommends installing reputable Python packages (eyeD3, mutagen, feedparser, requests, gpodder) to support these operations.
  • [PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection by parsing data from external RSS feeds.
  • Ingestion points: download_podcast_episodes function in SKILL.md (RSS URL parameter).
  • Boundary markers: None.
  • Capability inventory: subprocess.run (ffmpeg), requests.get (media download), and file system write.
  • Sanitization: Media titles are sanitized via alphanumeric filtering to prevent path traversal when creating files.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 4, 2026, 07:28 PM
Security Audit — agent-trust-hub — audio-extraction