skill_proposal

Manage approval-gated skill proposals. Create proposals for missing capabilities, list pending proposals, evaluate drafts, and approve/reject proposals.

SERVERCoWork OS SOURCECoWork-OS/CoWork-OS

Medium RISK CLASS

Category Write

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/cowork-os/skill-proposal.md

WHAT IT DOES

What skill_proposal does on CoWork OS

AI agents use skill_proposal to create or update resources in CoWork OS, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your CoWork OS environment.

RISK

Why skill_proposal is rated Medium

This tool creates and modifies proposal records in a gated approval workflow. While it affects the state of skill proposals (a Write operation), the severity is medium rather than high because: (1) proposals are typically reversible/amendable, (2) approval gates limit autonomous harm, and (3) the tool operates within a controlled governance layer rather than directly executing external code or destructing data.

From the tool's definition Tool description states 'Create proposals for missing capabilities', 'approve/reject proposals' — these are create and modify operations on proposal records. No irreversible deletion or financial impact, nor execution of arbitrary code.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs skill_proposal 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_proposal, this is the rule to start with:

skill_proposal Rate-limited

skill_proposal stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "skill_proposal": {
      "limits": [
        {
          "counter": "skill_proposal_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect CoWork OS, apply this rule, and every skill_proposal call is checked against it from then on.

FAQ

Questions about skill_proposal

What does the skill_proposal tool do? +

Manage approval-gated skill proposals. Create proposals for missing capabilities, list pending proposals, evaluate drafts, and approve/reject proposals. It is categorised as a Write tool in the CoWork OS MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on skill_proposal? +

Register the CoWork OS MCP server in PolicyLayer and add a rule for skill_proposal: 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.

What risk level is skill_proposal? +

skill_proposal is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit skill_proposal? +

Yes. Add a rate_limit block to the skill_proposal 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.

How do I block skill_proposal completely? +

Set action: deny in the PolicyLayer policy for skill_proposal. 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.

What MCP server provides skill_proposal? +

skill_proposal 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.

KEEP EXPLORING

More on CoWork OS, and thousands of servers like it.

This server

All 342 CoWork OS tools →

Across the catalogue

The MCP Attack Database →

Guides

Govern customer-ops agents →Argument validation →Scoped token →