AI agents call get_skill to retrieve information from Stac2026 without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves skill content by name, which is a read-only query operation. There is no indication of data creation, modification, deletion, code execution, or financial transactions. The action is non-destructive and carries minimal security risk unless the skill repository contains highly sensitive information, but that would be a data governance issue rather than a tool capability issue.
From the tool's definition Tool description states 'Get the full content of a skill by name' — a retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
Get the full content of a skill by name. It is categorised as a Read tool in the Stac2026 MCP Server, which means it retrieves data without modifying state.
Register the Stac2026 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 Stac2026. 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 Stac2026 MCP server (ktg-one/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 →