feishu-bot-dev

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The guide shows hardcoded App ID/App Secret values in code samples and configuration (and examples that pass secrets as function args or CLI/env values), which would require an agent to handle or echo secret values verbatim to reproduce those examples.

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

• Third-party content exposure detected (high risk: 0.75). 该技能的运行时工作流会通过飞书事件订阅接收“im.message.receive_v1”等外部用户消息，并在 handle_message_receive 中读取 data.event.message.content（外部作者的自由文本）后可能被用于后续 LLM 上下文/回复生成。

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The MCP Server integration config runs remote code via npx/npm (e.g., "npx @larksuiteoapi/lark-mcp" / "npm install @larksuiteoapi/lark-mcp"), which fetches and executes a package at runtime and is presented as a required dependency for the AI Agent integration.