Read the instruction manual (SKILL.md) and file structure of a locally installed skill.
AI agents call skills_get_details to retrieve information from Skills MCP 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 local skill documentation and metadata. No side effects, no code execution, no data modification. The worst-case misuse would be information disclosure of skill details, which poses minimal risk.
From the tool's definition The tool 'reads the instruction manual (SKILL.md) and file structure of a locally installed skill' — purely retrieves and displays information about existing skills without modifying, executing, or deleting anything.
Attacks that exploit this kind of access
Read the instruction manual (SKILL.md) and file structure of a locally installed skill. It is categorised as a Read tool in the Skills MCP MCP Server, which means it retrieves data without modifying state.
Register the Skills MCP server in PolicyLayer and add a rule for skills_get_details: 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 MCP. Nothing to install.
skills_get_details 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_get_details 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_get_details. 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_get_details is provided by the Skills MCP server (leezhuuuuu/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 →