skills.rest
pluginagentmarketplace
pluginagentmarketplaceCOMMUNITY
Explore all skills by this author →
GitHub

red-team-frameworks

Orchestrate automated red-team tests across PyRIT, garak, Counterfit, ART, and TextAttack.

3|Updated Nov 18, 2025
Search Tags:#automation#frameworks#LLM#orchestration#comparison#red-team#security-testing
One-click install
npx skills add https://github.com/pluginagentmarketplace/custom-plugin-ai-red-teaming --skill red-team-frameworks
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: red-team-frameworks
Source: https://github.com/pluginagentmarketplace/custom-plugin-ai-red-teaming/tree/main/skills/red-team-frameworks
Command: npx skills add https://github.com/pluginagentmarketplace/custom-plugin-ai-red-teaming --skill red-team-frameworks

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

The Red-Team Frameworks skill consolidates multiple AI red-teaming tools into a single, orchestrated interface to streamline security testing and vulnerability discovery across LLMs and ML models.

Core Features & Use Cases

  • Integrates PyRIT, garak, Counterfit, ART, and TextAttack for end-to-end testing.
  • Provides a unified configuration and results workflow to compare frameworks and generate actionable findings.
  • Use case: security team evaluates a new LLM deployment by running parallel attacks across frameworks and consolidating findings into a unified report.

Quick Start

Install dependencies and run the framework selector to explore recommended tools, then configure a test target and execute attacks.

Frequently Asked Questions about red-team-frameworks

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

FAQPage Schema
How do I run automated security testing across multiple LLM red-team frameworks?▼

Automated security testing across LLM red-team frameworks is orchestrated by configuring target parameters, selecting tools like PyRIT or garak, and executing parallel attacks to produce structured findings.

What is the best way to compare AI red-team frameworks like PyRIT, garak, and Counterfit?▼

Comparing AI red-team frameworks involves running orchestrated tests across tools like PyRIT, garak, and Counterfit to generate structured outputs with actionable findings and framework mappings.

Can I use this skill to run vulnerability discovery for enterprise LLM deployments?▼

Vulnerability discovery for enterprise LLM deployments is supported by applying automated red-team tests across multiple frameworks and consolidating findings into a unified report.

How do I configure target parameters for automated attacks with ART and TextAttack?▼

Configuring target parameters for automated attacks with ART and TextAttack involves selecting appropriate frameworks and setting up test targets to execute orchestrated security assessments.

Does this red-team tooling support parallel attacks across different ML security frameworks?▼

Parallel attacks across different ML security frameworks are supported through orchestration that integrates PyRIT, garak, Counterfit, ART, and TextAttack into a unified testing workflow.

Why do I need an orchestrated interface for AI red-teaming tools?▼

An orchestrated interface for AI red-teaming tools is needed to consolidate multiple testing frameworks into a unified configuration and results workflow, streamlining vulnerability discovery.

Related Skills

Explore More Software Engineering Skills→
MHaggisMHaggis
471

Custom Atomics Deployment

Create, deploy, and execute custom Atomic Red Team YAML tests.

Community
Advanced
pluginagentmarketplacepluginagentmarketplace
3

vulnerability-discovery

Identify and analyze AI/LLM vulnerabilities via structured threat modeling and attack surface analysis.

Community
Advanced
chrismcmackenchrismcmacken

review-artifacts

Triage artifact scan results to surface reportable bug bounty findings.

Community
Intermediate
brucesongsbrucesongs
60

llm-red-team

Expose LLM system vulnerabilities via a six-phase red-team workflow.

Community
Advanced