bmad-product-brief

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly launches a Web Researcher subagent (agents/web-researcher.md) during Stage 2 (prompts/contextual-discovery.md and SKILL.md) to execute targeted web searches and synthesize public web content, which is untrusted third-party material that the agent reads and uses to influence drafting and decisions.