competitor-ad-intelligence

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

• Third-party content exposure detected (low risk: 0.10). The required workflow actively searches via web_search and visits the Meta Ad Library and Google Ads Transparency Center, then fetches competitor landing pages, so outsider-authored ad copy and page text are only ingested after the agent selects and retrieves them, which is the low-risk pattern.