solution-explorer

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

• Third-party content exposure detected (high risk: 0.90). The skill's Phase 2 "Research each paradigm substantively" step explicitly instructs the agent to "Use web search, documentation lookups, and codebase exploration" so the agent will fetch and interpret open/public third‑party content (web pages/docs) and use that information to drive decisions, creating a clear vector for indirect prompt injection.