brainstorming-with-explorer-challenger-teams

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs agents to read "open issues or feature requests" as part of the project brief (Step 1) and even suggests "research competitors or user feedback" for product brainstorming, which requires fetching and interpreting public/user-generated web content that could be untrusted.