AI agents call get_skill to retrieve information from Zanat without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only operation that queries and returns data about a skill without any side effects. It matches the Read category pattern of retrieving information (get, fetch). The low severity reflects that accessing skill content poses minimal risk—no data is modified, deleted, or executed. The high confidence is based on the clear retrieval semantics indicated by both the tool name and its functional description.
From the tool's definition The tool 'get_skill' retrieves the full content of a specific skill by its name. The description indicates a retrieval operation with no modification, deletion, or execution capability.
Attacks that exploit this kind of access
Get the full content of a specific skill by its full name (e.g. It is categorised as a Read tool in the Zanat MCP Server, which means it retrieves data without modifying state.
Register the Zanat MCP server in PolicyLayer and add a rule for get_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 Zanat. Nothing to install.
get_skill 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 get_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 get_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.
get_skill is provided by the Zanat MCP server (@iamramo/zanat-mcp). 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 →