munger-perspective

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

• Third-party content exposure detected (high risk: 1.00). Yes — the SKILL.md "Step 2: 芒格式研究" explicitly requires using tools (e.g., WebSearch) to fetch and interpret public third‑party content (latest news, financials, criticism, web sources) as part of its mandatory research workflow, which can materially influence the agent's decisions.

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

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