ingest-youtube

Pass

Audited by Gen Agent Trust Hub on Jun 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The script ingest.py executes the yt-dlp binary using the subprocess.run method. It passes arguments as a list rather than a shell string, which is a secure practice that mitigates shell injection risks.
  • [EXTERNAL_DOWNLOADS]: The skill connects to YouTube to download metadata and subtitle files. This communication is handled by yt-dlp, a standard tool for this purpose, and targets a well-known service.
  • [PROMPT_INJECTION]: The skill ingests untrusted content from YouTube transcripts which could potentially contain adversarial instructions. The script implements boundary markers using YAML frontmatter and performs sanitization by cleaning VTT timing markers and slugifying metadata to prevent path traversal when writing files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 25, 2026, 09:53 AM
Security Audit — agent-trust-hub — ingest-youtube