targeting-expert

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

• Third-party content exposure detected (high risk: 0.90). The skill calls functions like search_interests, get_interest_suggestions, get_custom_audiences and search_geo_locations that pull interests/audiences/locations from Facebook/Instagram (social media) data — untrusted, user-generated third‑party content that the agent is expected to read and interpret.