genius

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

• Third-party content exposure detected (low risk: 0.10). The agent searches Genius (genius.com) and reads song lyrics, annotations, and artist content authored by third parties on the platform.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs connection to and execution against an external remote MCP server hosted at unbrowse.ai via HTTP transport, which provides operational tools and instructions with common/reputable unofficial third-party provenance.