---
name: "llm-red-teaming-prompt-jailbreak-audit"
description: "Audit language model applications against prompt injection, jailbreaks, and data extraction."
metadata:
  author: "Microsoft"
  version: "1.0.0"
  runtime_compatibility:
    - "codex"
    - "claude-code"
    - "cursor"
    - "windsurf"
triggers:
  - "test prompt injection vulnerability"
  - "red team llm application"
  - "audit system prompt leakage"
permissions:
  fs_read: true
  fs_write: "workspace"
  shell_exec: false
  net_access: false
---

# LLM Red Teaming & Adversarial Jailbreak Audit

Performs red-teaming security assessments on LLMs: indirect prompt injection, system prompt extraction, multi-turn escalation, delimiter collision attacks, and defense verification.

## When to Invoke
Invoke this skill whenever you need to:
- test prompt injection vulnerability
- red team llm application
- audit system prompt leakage

## Execution SOP & Rules
1. Test across common attack vectors: direct injection, indirect payload, delimiter collision, and leetspeak.
2. Verify whether the model executes instructions contained inside untrusted retrieved context.
3. Implement input boundary tags (e.g. <untrusted_user_input>) and explicit system constraints.
4. Document identified vulnerabilities with reproducible attack payloads and remediation advice.

## Verification Checklist
- Run local linting, syntax validation, and type-checks before reporting completion.
- Ensure all created or modified files adhere to workspace boundaries and avoid uncommitted secrets.
- Verify tests or build commands exit cleanly with return code 0.