Skill
Invoke a skill by ID when one clearly matches the task. If a matching skill exists, call Skill before using other tools or drafting the final answer.
This record as markdown: /tools/cowork-os/skill.md
What Skill does on CoWork OS
AI agents invoke Skill to trigger actions in CoWork OS. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
Why Skill is rated High
This tool invokes skills by ID, which is an Execute operation. The actual effects are entirely dependent on what the invoked skill does, creating a high blast radius if an AI agent misuses the skill ID or invokes the wrong skill.
From the tool's definition The tool 'Invoke a skill by ID' executes external operations ('call Skill before using other tools') whose effects depend on the skill ID argument provided.
Attacks that exploit this kind of access
The rule that runs Skill safely
PolicyLayer is an MCP gateway: it sits between your AI agents and CoWork OS, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For Skill, this is the rule to start with:
Skill stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect CoWork OS, apply this rule, and every Skill call is checked against it from then on.
Questions about Skill
Invoke a skill by ID when one clearly matches the task. If a matching skill exists, call Skill before using other tools or drafting the final answer. It is categorised as a Execute tool in the CoWork OS MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the CoWork OS MCP server in PolicyLayer and add a rule for Skill: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches CoWork OS. Nothing to install.
Skill is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the Skill rule in your PolicyLayer 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 PolicyLayer policy for Skill. 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.
Skill is provided by the CoWork OS MCP server (CoWork-OS/CoWork-OS). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on CoWork OS, and thousands of servers like it.
Across the catalogue