Security scan for skills and agent config
secure_scanScan a folder for risky agent setup—secrets and pipe-to-shell skills, unpinned or remote MCP servers, broad permissions, risky dependencies—and return severity-ranked fixes. Read-only.
Instructions
Scan a folder for risky agent setup: secrets and pipe-to-shell in skills, unpinned or remote-package MCP servers in .mcp.json, broad permissions in .claude/settings.json, risky dependencies in skill scripts. Returns findings by severity with a fix for each. Read-only.
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "secure_scan"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| path | No | The folder to scan. Relative paths resolve from the folder the server was started in. Default "." |