skills.rest
bpnrockstar
bpnrockstarCOMMUNITY
Explore all skills by this author →
GitHub

llm-redteam

Test LLM applications for prompt injection, jailbreak, and guardrail bypass vulnerabilities.

Updated Jul 1, 2026
Search Tags:#security testing#LLM#jailbreak#prompt injection#red teaming
One-click install
npx skills add https://github.com/bpnrockstar/UnifiedBugHunter --skill llm-redteam
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: llm-redteam
Source: https://github.com/bpnrockstar/UnifiedBugHunter/tree/main/skills/llm-redteam
Command: npx skills add https://github.com/bpnrockstar/UnifiedBugHunter --skill llm-redteam

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill provides a comprehensive methodology for testing LLM applications against the latest prompt injection, jailbreak, and guardrail bypass techniques, ensuring security and robustness.

Core Features & Use Cases

  • Comprehensive Methodology: Covers 15+ attack classes from 2024-2026 research, including direct/indirect injection, token smuggling, adversarial poetry, and more.
  • Automated Testing: Utilizes 180+ payloads for direct testing against LLMs.
  • Use Case: For security professionals and red teamers who need to ensure LLM applications are secure against sophisticated attacks.

Quick Start

Run the llm-redteam skill to list all available payloads.

Frequently Asked Questions about llm-redteam

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I test my LLM application for prompt injection vulnerabilities?▼

You can test LLM applications for prompt injection vulnerabilities by running this skill, which applies 180+ payloads across 15+ attack classes to identify guardrail bypasses and security weaknesses.

What is the best way to perform jailbreak testing on LLMs?▼

The best way to perform jailbreak testing on LLMs is using a comprehensive red teaming methodology with diverse payloads, including direct injection, token smuggling, and adversarial poetry techniques.

Can I use automated payloads for LLM red teaming?▼

Yes, you can use automated payloads for LLM red teaming by running the skill to list and apply 180+ distinct attack payloads directly against your target LLM application.

What attack classes are covered in LLM security testing?▼

LLM security testing here covers 15+ attack classes from 2024-2026 research, including direct and indirect prompt injection, token smuggling, and adversarial poetry.

Do I need prior red teaming experience to test LLM guardrails?▼

Prior red teaming experience is expected, as this skill is designed for security professionals who need to ensure LLM applications are secure against sophisticated guardrail bypass techniques.

When should I use automated payload testing for LLM security?▼

You should use automated payload testing for LLM security when you need to systematically evaluate applications against a comprehensive set of known jailbreak and prompt injection techniques.

Related Skills

Explore More Software Engineering Skills→
davduncdavdunc

Security

Route security assessments across recon, web testing, and prompt-injection scenarios.

Community
Advanced
maruakshaymaruakshay
4

core-llm-prompt-security

Identify and mitigate prompt injection and jailbreak risks in LLM prompts.

Community
Advanced
williamzujkowskiwilliamzujkowski
17

ci-cd-pipelines

Automate CI/CD standards for GitHub Actions and GitLab CI pipelines.

Community
Advanced
SignmanalSignmanal
1

godmode

Bypass LLM safety filters for authorized security testing via OpenRouter.

Community
Advanced