ads-landing

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

• Third-party content exposure detected (high risk: 0.90). The skill's Phase 2 explicitly requires a WebFetch of the landing page ("Phase 2: WebFetch the landing page") and then reads headlines, body copy, CTAs, and PSI results from arbitrary public landing pages to score and decide fixes, so untrusted third-party page content can directly influence the agent's decisions and actions.