youtube-automation

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs users to add an external MCP server endpoint (https://rube.app/mcp) to their client environment. This server provides the tool definitions and facilitates execution of YouTube API commands.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from external sources, which could be exploited to influence agent behavior.
  • Ingestion points: The skill retrieves external content through YOUTUBE_LIST_COMMENT_THREADS (ingesting user-generated comments) and YOUTUBE_SEARCH_YOU_TUBE (ingesting video metadata and search results).
  • Boundary markers: There are no instructions provided to the agent to distinguish between its primary goals and instructions that might be embedded in the retrieved YouTube content.
  • Capability inventory: The skill provides high-impact capabilities including YOUTUBE_UPLOAD_VIDEO, YOUTUBE_UPDATE_VIDEO, and YOUTUBE_SUBSCRIBE_CHANNEL which could be misused if the agent obeys instructions found in comments.
  • Sanitization: Documentation mentions that angle brackets (< >) are stripped from tags, but no comprehensive sanitization or filtering is described for processing comment threads or search descriptions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 06:59 PM
Security Audit — agent-trust-hub — youtube-automation