zettaranc-perspective

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

• Third-party content exposure detected (high risk: 1.00). The skill's required workflow (SKILL.md Step 2: "必须使用工具（WebSearch等）获取真实信息") explicitly instructs the agent to fetch and research public/web sources (e.g., B站直播 recordings, fan transcripts, comments and other public articles listed in the references), so it ingests untrusted user-generated third‑party content that will directly influence analysis and actions.