bmad-agent-marketing-pr

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow (Outputs and Deliverables → Response Protocol step 1) explicitly instructs the agent to, when repo context is missing, "proceed from ... live website or profile footprint," which means the agent will fetch and read public third‑party web/social content and use it to drive PR decisions and outputs—exposing it to untrusted, user-generated web content that can influence actions.