loading…
LLM attack
/
tools
/ tool editor
llm__analyze_prompt
name (registry, task__-namespaced)
description
Submit suspicious prompt for behavioral analysis and threat classification
behavior spec (steers the decoy + judge)
state-changing
JSON Schema (arguments)
✓ valid · 6 props · 1 required
{ "type": "object", "required": [ "prompt_text" ], "properties": { "context": { "type": "string" }, "priority": { "enum": [ "low", "medium", "high", "critical" ], "type": "string", "default": "medium" }, "source_ip": { "type": "string" }, "user_agent": { "type": "string" }, "prompt_text": { "type": "string" }, "model_target": { "type": "string" } } }
Save tool
registry name changes propagate to the decoy surface on the next drain