shield_validate_output
Check model output before it is used: secret and PII leakage, exfiltration links, active content, dangerous shell patterns, optional schema and grounding checks (0.015 USDC per call)
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": {
"output": "<output>"
},
"name": "shield_validate_output"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| output | Yes | Raw model output (max 200000 characters) | |
| schema | No | JSON Schema subset to enforce | |
| source | No | Source text for a grounding check | |
| system_prompt | No | Your system prompt, used only in this request to detect it being echoed back |