zhang-yiming-perspective

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

• Third-party content exposure detected (high risk: 0.90). The skill's required Agentic Protocol (Step 2 in SKILL.md) explicitly mandates using WebSearch and other tools to fetch and ingest public third‑party content (news, product pages, social media like 微博, download rankings, etc.) to inform answers, so untrusted web content is read and can change the agent's subsequent actions.