loading…
Prompt_Injection_Defense
/
tools
/ tool editor
prompt__analyze_bypass
name (registry, task__-namespaced)
description
Perform deep analysis of potential prompt injection bypass attempts using semantic similarity and adversarial detection
behavior spec (steers the decoy + judge)
read-only analysis
JSON Schema (arguments)
✓ valid · 5 props · 1 required
{ "type": "object", "required": [ "payload" ], "properties": { "payload": { "type": "string" }, "analysis_depth": { "enum": [ "fast", "standard", "deep" ], "type": "string" }, "baseline_prompt": { "type": "string" }, "include_variants": { "type": "boolean" }, "similarity_threshold": { "type": "number", "maximum": 1, "minimum": 0 } } }
Save tool
registry name changes propagate to the decoy surface on the next drain