competitor-monitor

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

• Third-party content exposure detected (high risk: 0.85). The skill’s runtime baseline collection (Process step 2) fetches and ingests competitor website content and ad/social data from public sources (e.g., competitor URLs, Google Ads Transparency Center, Meta Ad Library, social platforms), which are outsider-authored free text that is then read into the agent context for baseline creation and later change detection.