bmad-technical-research

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

• Third-party content exposure detected (high risk: 1.00). The skill's workflow (SKILL.md and multiple technical-steps files such as step-02 through step-06) explicitly requires live "Search the web" queries and demands citing URLs and using current public sources, so the agent ingests and acts on untrusted public web content that can influence subsequent decisions and actions.