meta-ad-builder

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

• Third-party content exposure detected (medium risk: 0.65). Outsider free text can enter the LLM context via Phase 1 research: pull-top-ads.py and pull-competitor-ads.py fetch competitor/other-party ad copy (e.g., ad_creative_bodies/creative fields and ad_snapshot_url-derived text) from Meta’s Ad Library at runtime, which the agent then uses to “mirror the voice and patterns of the winners” when generating copy.json for Phase 2.