Multi-AI Consultant

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly calls the Gemini CLI with --google-search/grounding to perform web research and then ingests the external AI's complete response into Claude's 5-part synthesis (e.g., /consult-gemini and the "Other AI's Analysis" step), which exposes the agent to untrusted public web content.