financial-expert

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill tells the agent to request and embed the user's API key into shell commands (e.g., export DASHSCOPE_API_KEY=sk-你的APIKey and bl auth login --api-key sk-你的APIKey), which requires the LLM to handle and output secret values verbatim.

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

• Third-party content exposure detected (medium risk: 0.30). 工作流在调用 bl mcp call market-cmapi00073529.FinancialResearchReport 与 ...AnnouncementData 时，会读取由查询条件触发的“券商研报/上市公司公告原文”（非结构化文本/原文片段）并返回给用户，且该查询条件由用户自由输入导致间接注入风险。