Wework
Analysis
This is an instruction-only Enterprise WeChat API guide; it does not install or run code, but it describes credentials and APIs that can change or message an organization.
Findings (2)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
删除部门:`GET /cgi-bin/department/delete?id=ID` ... 发送应用消息:`POST /cgi-bin/message/send` ... `"touser": "@all"`
The skill documents mutating and broadcast-capable Enterprise WeChat API operations. This is expected for a developer assistant, but these operations could affect many users if implemented with real credentials.
Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.
企业微信 API 基于 corpid + corpsecret 获取 access_token,不同 secret 对应不同权限范围
The skill explains the use of Enterprise WeChat secrets and access tokens, including secrets for address book and customer-contact access. This is purpose-aligned, but those credentials can grant sensitive enterprise permissions.
