---
name: undominated-prompt-leakage-resilience-audit
description: Evaluates system prompt confidentiality retention under adversarial prompt extraction and reconstruction attacks.
license: MIT
metadata:
  author: Undominated.ai
  version: "1.0.0"
  tags: ["prompt-leakage", "jailbreak", "security", "confidentiality"]
---

# Prompt Extraction & Leakage Resilience Audit

Evaluates system prompt confidentiality retention under adversarial prompt extraction and reconstruction attacks.

## When to Use
Deploy before exposing proprietary system instructions in public-facing conversational agents.

## Limitations
System prompts containing sensitive credentials violate security policies; never store secrets in prompts.

## Verification Script
Run the deterministic stdlib checker:
```bash
python3 scripts/check.py examples/synthetic.json
```
Exits `0` on verified pass, `1` on failed assertion, `2` on malformed input.