qcc-bidding

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). 该 Skill 要求用户直接提供 API Key 并指示 Agent 自动将该密钥原文写入 .env 文件并用于验证请求，意味着密钥会以明文出现在模型处理与输出流程中，存在高风险的密钥泄露和外泄。

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

• Third-party content exposure detected (high risk: 0.75). Runtime LLM context can include outsider-authored free text because scripts/qcc_client.js/scripts/qcc_bidding_fmt.js fetches company/risk/operation data from https://agent.qcc.com/mcp/<server>/stream and then parses d.result.content[0].text (which is untrusted text originating from third-party Qichacha/public records) into the agent’s output context.