lark-openapi-explorer

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

• Potentially malicious external URL detected (high risk: 0.90). The skill performs runtime WebFetch calls to external OpenAPI markdown (e.g. https://open.feishu.cn/llms.txt and related https://open.feishu.cn/document/.../.md) which are parsed and injected into the agent's context to determine API calls and behavior, so the fetched content directly controls prompts and is required for operation.