Scan a path
scan_pathRun a read-only, offline scan of a file or directory to detect malicious or risky content like prompt injection before installing or enabling a skill, plugin, hook, or MCP server.
Instructions
Scans one file or directory (a skill folder, plugin, hook script, MCP server source or MCP config) for malicious or risky content, such as prompt injection, hidden text, credential theft and data exfiltration. Useful before a skill, plugin or server is installed, enabled or run. Read-only and offline: nothing is executed, written or sent anywhere.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"path": "<path>"
},
"name": "scan_path"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| deep | No | Also walk node_modules, virtualenvs and caches. | |
| path | Yes | File or directory to scan. Relative paths resolve against the server working directory; a leading ~ means the home directory. | |
| max_findings | No | Largest number of findings to return, most severe first. | |
| min_severity | No | Leave out findings below this severity. | low |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| tool | Yes | ||
| counts | Yes | ||
| skipped | Yes | ||
| targets | Yes | ||
| version | Yes | ||
| complete | Yes | False when some files or folders were not scanned; a scan that is not complete is not a clean result. | |
| findings | Yes | ||
| filesScanned | Yes | ||
| skippedFiles | Yes | ||
| highestSeverity | Yes | ||
| omittedFindings | Yes |