AI agents call skillet_search to retrieve information from Skillet without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only search operation against a skill registry. It retrieves and returns information about available skills without creating, modifying, deleting, or executing any actions. The search function is analogous to querying a catalog or database for informational purposes only, making it a Read category tool with low severity risk.
From the tool's definition Tool enables 'search' and 'returns matching skills' - a retrieval operation with no modification of state. Description indicates it queries a registry and returns results without side effects.
Attacks that exploit this kind of access
Search the skillet registry for AI agent skills (SKILL.md). Returns matching skills with. It is categorised as a Read tool in the Skillet MCP Server, which means it retrieves data without modifying state.
Register the Skillet MCP server in PolicyLayer and add a rule for skillet_search: 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 Skillet. Nothing to install.
skillet_search 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 skillet_search 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 skillet_search. 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.
skillet_search is provided by the Skillet MCP server (jnmetacode/skillet). 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 →