global-legal-counsel

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

• Third-party content exposure detected (high risk: 0.90). The skill's required research workflow explicitly tells the agent to "优先调用当前搜索/研究能力" and to rely on one‑hand sources for current law (see SKILL.md Research & Evidence and references/research-and-evidence.md), which requires fetching and interpreting public web content (including media, forums, and other external sources) that could contain untrusted, user-generated instructions influencing legal analysis and next actions.