triage
Evaluate a single security finding to determine if it is real, exploitable, and non-duplicate. Get a verdict, adjusted severity, and a SAFE negative control to confirm or dismiss it.
Instructions
Adversarially triage ONE finding: is it real, exploitable and non-duplicate? Returns a verdict, dup-likelihood, adjusted severity, and the SAFE negative control to run to confirm or kill it. Args: finding_json: a single finding object as JSON
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": {
"finding_json": "<finding_json>"
},
"name": "triage"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| finding_json | Yes |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |