naval-perspective

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly requires in "Step 2: Naval式研究" that the agent "必须使用工具（WebSearch等）获取真实信息，不可跳过" and instructs searching public sources (e.g., product pages, developer/community feedback, industry news), so the agent will fetch and interpret untrusted user-generated web content that can materially influence its decisions.

MEDIUM W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).

• Hidden Unicode characters detected (1 type(s) found)