scan_agent_action
Evaluate agent actions before execution to detect security risks. Returns ALLOW, WARN, or BLOCK for commands, file operations, and more.
Instructions
Pre-execution security check for agent actions (bash, file_write, file_read, http_request, file_delete, cron, process_spawn, git, docker). Returns ALLOW/WARN/BLOCK.
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": {
"action_type": "<action_type>",
"action_value": "<action_value>"
},
"name": "scan_agent_action"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| verbosity | No | Response detail level: 'minimal' (action only), 'compact' (default), 'full' (all details) | |
| action_type | Yes | Type of agent action to evaluate | |
| action_value | Yes | The command, file path, URL, or structured input to check |