peekaboo

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

• Third-party content exposure detected (high risk: 0.75). The skill’s workflow routes to agents that accept runtime user-provided URLs (e.g., “DESIGN_URL” / “IMPLEMENTATION_URL” for the Design QA Validator), which are then fetched/parsed as readable web content and fed into the agent’s LLM context, creating an outsider free-text injection surface.