competitor-ads-analyst

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly directs the agent to extract and analyze ads from public ad libraries (see "Ad Library Access" listing facebook.com/ads/library, adstransparency.google.com, library.tiktok.com, linkedin.com/ad-library and the "Extract Ads" workflow), which requires ingesting untrusted third‑party user-generated/public web content and using it to drive analysis and recommendations, enabling indirect prompt injection.