loading…
LLM attack
/
tools
/ tool editor
llm__export_forensics
name (registry, task__-namespaced)
description
Generate forensic package with attack artifacts, conversation logs, and timeline for incident response
behavior spec (steers the decoy + judge)
read-only
JSON Schema (arguments)
✓ valid · 6 props · 1 required
{ "type": "object", "required": [ "incident_id" ], "properties": { "incident_id": { "type": "string" }, "time_window": { "enum": [ "attack_only", "1h_before", "24h_before", "full_session" ], "type": "string" }, "sanitize_pii": { "type": "boolean", "default": true }, "export_format": { "enum": [ "json", "csv", "stix", "misp" ], "type": "string", "default": "json" }, "include_payloads": { "type": "boolean", "default": true }, "include_model_responses": { "type": "boolean", "default": false } } }
Save tool
registry name changes propagate to the decoy surface on the next drain