youtube-automation

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXFILTRATION]: The skill configures a connection to the external Rube MCP server at https://rube.app/mcp to access YouTube automation tools. This network communication is a core requirement for the skill's primary functionality and is documented for user configuration.\n- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it processes untrusted data from external YouTube sources such as search results and comments.\n
  • Ingestion points: Untrusted data enters the context through tools like YOUTUBE_SEARCH_YOU_TUBE and YOUTUBE_LIST_COMMENT_THREADS as described in the Core Workflows.\n
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands are provided in the skill documentation to isolate external content.\n
  • Capability inventory: The skill possesses extensive write capabilities, including YOUTUBE_UPLOAD_VIDEO, YOUTUBE_UPDATE_VIDEO, and YOUTUBE_SUBSCRIBE_CHANNEL, which could be targeted by injected instructions.\n
  • Sanitization: The documentation does not specify any sanitization or validation steps for handling external strings retrieved from the YouTube API.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 06:08 AM
Security Audit — agent-trust-hub — youtube-automation