bmad-prd

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

• Third-party content exposure detected (high risk: 0.70). The skill's required workflow (see "Discovery" — "Suggest research if needed and have subagents use web search tools as needed") plus the "{workflow.external_sources}" registry instruction makes the agent explicitly consult external web/search sources on demand, meaning it may fetch and interpret open/public third‑party content that can influence decisions.