impeccable

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

• Third-party content exposure detected (high risk: 0.90). The skill's critique/audit flows explicitly require opening and inspecting live web pages and injecting detection scripts (see reference/critique.md "Automated Detection" browser injection steps) and the brand guidance directs fetching public Unsplash images (reference/brand.md), so the agent will fetch and interpret untrusted, public third‑party content that can materially influence decisions and follow-up actions.