youtube-claims

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local Python scripts (fetch.py, doctor.py, cache.py, segments.py) to handle data processing, transcript slicing, and caching. These operations are limited to the skill's specific logic.
  • [EXTERNAL_DOWNLOADS]: Fetches video metadata, transcripts, and thumbnail images from YouTube and Google's infrastructure using well-known libraries like yt-dlp and youtube-transcript-api.
  • [PROMPT_INJECTION]: The skill processes untrusted external data in the form of YouTube transcripts, creating an indirect prompt injection surface.
  • Ingestion points: External transcripts are ingested through scripts/fetch.py and passed to the LLM.
  • Boundary markers: Prompts in the prompts/ directory use structured output requirements (JSON/Markdown) and explicit framing to constrain the model's behavior.
  • Capability inventory: The skill has the ability to make network requests (via yt-dlp) and write files to the ~/youtube-reports/ directory.
  • Sanitization: YouTube video IDs are strictly validated using regex in scripts/fetch.py before being used in commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 12:10 PM
Security Audit — agent-trust-hub — youtube-claims