skill-stocktake

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

• Third-party content exposure detected (high risk: 0.90). Phase 2's required checklist explicitly tells the launched subagent to "verify freshness of technical references (use WebSearch if tool names / CLI flags / APIs are present)", which directs the agent to fetch and interpret public web content (untrusted third‑party sources) that can materially influence evaluation verdicts.