paw-mkt-psychology

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

• Third-party content exposure detected (high risk: 0.80). The skill's required workflow explicitly directs the agent to audit user-provided public URLs ("Context C — Live Website URL Audit" in Shared Skill Patterns / Starting Context Router) and even instructs installing/using an agent-browser for browser-based research, so the agent will fetch and interpret arbitrary public webpages whose content could materially influence actions.