geo-monitor

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

• Third-party content exposure detected (high risk: 1.00). The skill's Process step 3 ("Test each query on each platform") explicitly fetches and records full responses from external AI platforms (ChatGPT, Perplexity, Gemini, AI Overviews, Copilot), and those untrusted third-party responses are read and used to score visibility and drive recommendations, creating a clear avenue for indirect prompt injection.