share-of-voice

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

• Third-party content exposure detected (high risk: 0.90). The skill's required Process steps (especially steps 2–5) explicitly pull and interpret open/public third-party data—e.g., organic search rankings, Google Ads and Meta Ads auction/insight data, Brandwatch social mentions, ad-library analysis, and AI engine citation audits (ChatGPT, Gemini, Perplexity, Copilot via geo-tracker.py and competitor-intelligence)—and use that untrusted/user-generated content to drive SOV calculations and follow-up decisions, creating a clear avenue for indirect prompt injection.