youtube-automation

Warn

Audited by Snyk on Feb 20, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.80). This skill explicitly calls public YouTube endpoints (e.g., the required YOUTUBE_SEARCH_YOU_TUBE in "Search YouTube Content" and other endpoints like YOUTUBE_VIDEO_DETAILS and YOUTUBE_LIST_COMMENT_THREADS listed in SKILL.md), so the agent ingests untrusted, user-generated content from YouTube that can influence subsequent actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 0.90). The skill requires contacting the MCP endpoint https://rube.app/mcp (via RUBE_SEARCH_TOOLS) at runtime to fetch current tool schemas that directly shape agent instructions and behavior, representing a required external control point.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 20, 2026, 08:20 AM