bmad-agent-tech-writer

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

• Third-party content exposure detected (high risk: 0.70). The skill's write-document.md instructs the agent to "Use a subprocess if available for any web search, research, or document review" and to "review documents and extract relevant information" as part of its Research step, which clearly entails ingesting public web/third-party content that could contain untrusted, user-generated instructions influencing the agent's behavior.