get_capability_graph
Map an agent's capabilities to reveal dangerous attack paths and compute an overall risk score from the capability graph.
Instructions
Return the agent's capability graph: nodes (agent/tool/capability), edges (danger=true when part of a detected attack path), detected attack paths, and an overall risk score.
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": {
"agentId": "<agentId>"
},
"name": "get_capability_graph"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| agentId | Yes | ID of the agent to inspect |