youtube

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill recommends installing the @maton-ai/cli package via NPM and the maton-ai/cli/maton formula via Homebrew to manage OAuth connections through the Maton service.
  • [DATA_EXFILTRATION]: The skill makes network requests to api.maton.ai and connect.maton.ai to proxy YouTube API calls. While these are necessary for the skill's function, they are external network operations to non-whitelisted domains.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests untrusted data and provides the agent with write capabilities. 1. Ingestion points: Data retrieved from YouTube search, video, and comment endpoints. 2. Boundary markers: No specific delimiters or instructions to ignore embedded commands are present. 3. Capability inventory: Write actions include posting comments, managing playlists, and subscribing to channels. 4. Sanitization: No validation or filtering of external content is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 05:12 AM