ah-create-tasks

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

• Third-party content exposure detected (high risk: 0.90). Step 9 ("Researcher") explicitly instructs the subagent to "spawn parallel research tasks to clarify any details using research from the web or context7 tool," meaning the agent will fetch and interpret open web content that is untrusted and can materially influence research.md, spawned tasks, and downstream decisions.