precision-oncology-zhcn

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs embedding an API key directly into a command-line URL (e.g., ...?apiKey=sk-xxxx / 你的API_KEY), which requires placing secrets verbatim into commands and risks secret exfiltration.

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

• Third-party content exposure detected (medium risk: 0.30). The skill’s required runtime workflow ingests user-authored free text by taking the user’s raw question (and multi-turn context) as the initial query to MCP search tools (e.g., the “首轮对话：使用用户的原始问题作为搜索查询” rule), even though it then retrieves and fetches provider content by IDs.