export_skill
AI agents use export_skill to create or update resources in PromStack MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your PromStack MCP Server environment.
Exporting prompts as Claude Skills is a write operation that creates new data/artifacts in a system (likely Claude's skill registry or files). While reversible (Skills can be deleted), it modifies system state by introducing new executable code structures. This is less severe than Execute (doesn't directly run code) but more than Read.
From the tool's definition Tool name 'export_skill' combined with server description stating it enables 'exporting prompts as Claude Skills' indicates the tool creates or outputs data artifacts (Skills). The empty description limits certainty.
Attacks that exploit this kind of access
export_skill. It is categorised as a Write tool in the PromStack MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the PromStack MCP Server MCP server in PolicyLayer and add a rule for export_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 PromStack MCP Server. Nothing to install.
export_skill 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 export_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 export_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.
export_skill is provided by the PromStack MCP Server MCP server (promstack-1/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →