influencer-discovery

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

• Third-party content exposure detected (high risk: 0.85). The skill’s runtime workflow for “Multi-Platform Search” and “Competitor Analysis” (e.g., hashtag research, tagged posts, creator marketplace/explore pages) would typically ingest outsider-authored free text from public social/web content (posts, captions, comments, bios) into the agent’s LLM context for screening and profile building.