Create or update a shared organization skill in Shellgate. Content must be full markdown with YAML frontmatter (name, description). These skills are shared across all agents.
AI agents use org_skill_upsert to create or update resources in Shellgate — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Shellgate environment.
The tool creates or updates skills that are shared organization-wide, affecting all agents using Shellgate. This is a reversible Write operation (skills can be updated or deleted by other tools), but with high severity due to the shared blast radius — a malicious skill could be deployed to all agents.
From the tool's definition Tool description states 'Create or update a shared organization skill' — this is a Write operation (create/update). The tool modifies shared state ('shared across all agents'), giving it broad impact.
Documented attack patterns abuse exactly the kind of access org_skill_upsert gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Shellgate, and nothing reaches the server without passing your rules. This is the rule we recommend for org_skill_upsert:
{
"version": "1",
"default": "deny",
"tools": {
"org_skill_upsert": {
"limits": [
{
"counter": "org_skill_upsert_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}org_skill_upsert 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.
Free to start. No card required.
Create or update a shared organization skill in Shellgate. Content must be full markdown with YAML frontmatter (name, description). These skills are shared across all agents. It is categorised as a Write tool in the Shellgate MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Shellgate MCP server in PolicyLayer and add a rule for org_skill_upsert: 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 Shellgate. Nothing to install.
org_skill_upsert is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the org_skill_upsert 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 org_skill_upsert. 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.
org_skill_upsert is provided by the Shellgate MCP server (matthiastjong/shellgate). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Shellgate, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
31 Shellgate tools catalogued and risk-classified — across an index of 43,000+ MCP servers.