brainstorm-ideas-existing

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

• Third-party content exposure detected (high risk: 0.90). SKILL.md explicitly tells the agent to "use web search to understand the product" when a user mentions a product URL and to read user-provided files, meaning it will fetch and interpret arbitrary public web pages/third-party content as part of its workflow (SKILL.md "Context" and "Instructions"), so untrusted content could influence decisions.