youtube-automation
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches MCP server configuration from the external endpoint
https://rube.app/mcpto enable YouTube automation capabilities. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from YouTube which could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: External data is ingested via
YOUTUBE_SEARCH_YOU_TUBE(search results),YOUTUBE_VIDEO_DETAILS(metadata), andYOUTUBE_LIST_COMMENT_THREADS(user comments). - Boundary markers: The instructions do not define delimiters or specific warnings to ignore embedded instructions within the ingested YouTube data.
- Capability inventory: The skill has the capability to perform write operations including uploading videos (
YOUTUBE_UPLOAD_VIDEO), updating video metadata (YOUTUBE_UPDATE_VIDEO), managing thumbnails (YOUTUBE_UPDATE_THUMBNAIL), and managing subscriptions (YOUTUBE_SUBSCRIBE_CHANNEL). - Sanitization: There is no evidence of sanitization, escaping, or validation of the content retrieved from YouTube before it is processed by the agent.
Audit Metadata