bmad-discovery-research

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

• Third-party content exposure detected (high risk: 0.80). The skill's Research workflow explicitly instructs "Use WebSearch liberally" to gather competitor analysis, market trends, and user sentiment from the open web (public websites and user reviews), so the agent will fetch and read untrusted third‑party content and could be exposed to indirect prompt injection.