Gate a risky action
jev_gateAssess risk of shell commands or file edits before execution. Get a risk score, production/data impact, and allow, confirm, or block recommendation to prevent dangerous actions.
Instructions
Screen an action (e.g. a shell command or file edit) before an agent runs it. Returns a risk score, whether it touches production/data, and a recommendation: allow / confirm / 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": "<action>"
},
"name": "jev_gate"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| action | Yes | The action about to run, e.g. the shell command or a description. | |
| context | No | Optional surrounding context / what the agent is doing. |