idea-validation-autopilot

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs running web-backed research (Step 2: "Run 4 parallel research tracks"), requires "citations and dated evidence" in outputs, and lists "web search + fetch for sources" in Quick Command Patterns, which means the agent will fetch and interpret open/public third-party content (untrusted/user-generated) that can materially influence scoring and decisions.