scope-grill

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

• Third-party content exposure detected (medium risk: 0.30). The required runtime workflow ingests the outsider user’s free-form message that triggers the skill (e.g., “start a pentest…”) and then sequentially asks for details like target, authorization, scope, and deliverables, without needing the agent to select any specific pre-existing item.