marketing-agency

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly states the agent will audit "live URL / profile" inputs and "audit that live presence first" (Starting Context Router / Step 1), meaning it will fetch and read public/untrusted web pages or social profiles provided by users and use that content to drive routing and actions.