loading…
LLM attack
/
tools
/ tool editor
llm__get_indicators
name (registry, task__-namespaced)
description
Retrieve threat indicators including malicious prompt patterns, adversary signatures, and behavioral IOCs
behavior spec (steers the decoy + judge)
read-only
JSON Schema (arguments)
✓ valid · 5 props · 0 required
{ "type": "object", "required": [], "properties": { "tags": { "type": "array", "items": { "type": "string" } }, "active_only": { "type": "boolean", "default": true }, "created_since": { "type": "string", "format": "date-time" }, "confidence_min": { "type": "number", "maximum": 1, "minimum": 0 }, "indicator_type": { "enum": [ "prompt_pattern", "user_behavior", "model_response", "network_signature" ], "type": "string" } } }
Save tool
registry name changes propagate to the decoy surface on the next drain