AI agents call skills_read to retrieve information from Skills without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries skill content by identifier without side effects. It is a straightforward read operation that fetches data from a skills catalog. The description explicitly states it 'reads' content rather than executing, modifying, or deleting it.
From the tool's definition Tool name 'skills_read' and description 'Read the content of a specific skill by its slug' indicate a retrieval operation with no modification or execution of skills.
Attacks that exploit this kind of access
Read the content of a specific skill by its slug. Sections control how much content is returned (to save context): -. It is categorised as a Read tool in the Skills MCP Server, which means it retrieves data without modifying state.
Register the Skills MCP server in PolicyLayer and add a rule for skills_read: 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 Skills. Nothing to install.
skills_read 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 skills_read 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 skills_read. 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.
skills_read is provided by the Skills MCP server (lucasromanzin/skills-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 →