AI agents call get_skill_frequency to retrieve information from Resume without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves and ranks skill frequency data from existing resume documents. It performs no side effects, creates no new data, executes no code, and destroys nothing. This is a straightforward Read operation. Severity is low because even if misused by an AI agent, it only exposes existing personal skill frequency information without enabling harmful actions.
From the tool's definition Tool description states 'Return badge skills ranked by how many resumes list them' — this is a retrieval/query operation that reads and aggregates data from local resume documents without modifying, executing, or deleting anything.
Attacks that exploit this kind of access
Return badge skills ranked by how many resumes list them, in descending order. It is categorised as a Read tool in the Resume MCP Server, which means it retrieves data without modifying state.
Register the Resume MCP server in PolicyLayer and add a rule for get_skill_frequency: 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 Resume. Nothing to install.
get_skill_frequency 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_frequency 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_frequency. 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_frequency is provided by the Resume MCP server (mnoomnoo/resume-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 →