architect

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

• Third-party content exposure detected (low risk: 0.10). During /architect Stage (c) the workflow can run a “Fetch from the web” researcher subagent (tool landscape and Agent Skill or MCP discovery), and it then ingests the free text extracted from web pages/registry results returned by that external browsing at runtime, before writing the spec.