ilya-sutskever-perspective

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md Agentic Protocol explicitly requires using external tools ("必须使用工具（WebSearch等）获取真实信息，不可跳过" in Step 2) to fetch and interpret public web content (news, tweets, podcasts, papers) as part of its research-before-answer workflow, which exposes the agent to untrusted third‑party content that could carry indirect prompt injections.