NYC

youtube-automation

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • Indirect Prompt Injection (LOW): The skill possesses a surface for indirect prompt injection by processing untrusted data from YouTube while having broad write permissions. * Ingestion points: Untrusted data enters the agent context via YOUTUBE_LIST_COMMENT_THREADS and YOUTUBE_SEARCH_YOU_TUBE (SKILL.md). * Boundary markers: There are no delimiters or instructions provided to ignore embedded commands within the fetched YouTube content. * Capability inventory: The skill includes powerful write tools such as YOUTUBE_UPLOAD_VIDEO, YOUTUBE_UPDATE_VIDEO, YOUTUBE_CREATE_PLAYLIST, and YOUTUBE_SUBSCRIBE_CHANNEL. * Sanitization: No evidence of data sanitization or validation before processing external content exists.
  • External Downloads (LOW): The skill directs the user to add an external MCP server from https://rube.app/mcp (SKILL.md). While this is the intended setup for the skill, the source is not on the predefined list of trusted external repositories.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:00 PM