列出所有 企业微信 SKILL（按能力域分组）。当用户咨询企业微信（企微/WeCom）相关开发时，先调用此工具查看有哪些 SKILL 可用，再用 read_wecom_skill 读取具体内容。 分组引导： - foundation（基座）：认证、OAuth、JSSDK、通讯录 → 所有场景的前置依赖 - messaging（消息）：消息发送、素材、客服、会议 → 消息与实时通信 - crm（客户关系）：客户管理、标签、群发、朋友圈 → 营销与私域 - office（办公协同）：审批、文档、日程、考勤 → 企业办公 - isv（服务商）：第三方应用、代开发 → ISV/代开发模式 - ...
Part of the Omnisockit MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call list_wecom_skills to retrieve information from Omnisockit without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though list_wecom_skills only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
tools:
list_wecom_skills:
rules:
- action: allowSee the full Omnisockit policy for all 2 tools.
Agents calling read-class tools like list_wecom_skills have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.
列出所有 企业微信 SKILL（按能力域分组）。当用户咨询企业微信（企微/WeCom）相关开发时，先调用此工具查看有哪些 SKILL 可用，再用 read_wecom_skill 读取具体内容。 分组引导： - foundation（基座）：认证、OAuth、JSSDK、通讯录 → 所有场景的前置依赖 - messaging（消息）：消息发送、素材、客服、会议 → 消息与实时通信 - crm（客户关系）：客户管理、标签、群发、朋友圈 → 营销与私域 - office（办公协同）：审批、文档、日程、考勤 → 企业办公 - isv（服务商）：第三方应用、代开发 → ISV/代开发模式 - advanced（高级）：会话存档、安全、数据智能 → 特殊场景. It is categorised as a Read tool in the Omnisockit MCP Server, which means it retrieves data without modifying state.
Add a rule in your Intercept YAML policy under the tools section for list_wecom_skills. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Omnisockit MCP server.
list_wecom_skills is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the list_wecom_skills rule in your Intercept policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the Intercept policy for list_wecom_skills. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
list_wecom_skills is provided by the Omnisockit MCP server (@omnisockit/mcp-server). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept