symphony-setup

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

• Third-party content exposure detected (medium risk: 0.30). The skill workflow involves reading Linear tickets and project lists via Linear MCP (lines 50-52, 144-149), which exposes the agent to outsider-authored free text from issue trackers.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs cloning and running code from an unofficial third-party GitHub repository (odysseus0/symphony), which constitutes an operational dependency with weak/unknown publisher provenance.