skills.rest
dreadnode
dreadnodeOFFICIAL
Explore all skills by this author →
Website𝕏@dreadnodeGitHub

attack-selection-guide

Select adversarial attack methods for AI red teaming assessments.

11|1|Updated May 4, 2026
Search Tags:#jailbreak#security-assessment#adversarial-testing#llm-security#ai-red-teaming#attack-selection#agentic-attacks
One-click install
npx skills add https://github.com/dreadnode/capabilities --skill attack-selection-guide
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: attack-selection-guide
Source: https://github.com/dreadnode/capabilities/tree/main/capabilities/ai-red-teaming/skills/attack-selection-guide
Command: npx skills add https://github.com/dreadnode/capabilities --skill attack-selection-guide

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Security teams conducting AI red teaming assessments often struggle to select the most effective adversarial attacks for their specific target type, compute budget, and defensive controls, leading to wasted effort and incomplete test coverage.

Core Features & Use Cases

  • Target-Type Guided Selection: Provides clear branching for LLMs, agentic systems, and custom API endpoints to match attack methods to the target architecture.
  • Budget & Defense Aligned Recommendations: Maps attack algorithms and transforms to available compute budgets and known defensive controls like content moderation or input sanitization.
  • Comprehensive Threat Coverage: Includes pairing recommendations for over 20 threat categories including jailbreaks, MCP attacks, RAG poisoning, and exfiltration testing.
  • Use Case: A red teamer testing a customer service chatbot with strong rate limiting can quickly identify that the pair attack algorithm paired with base64 encoding transforms is the most efficient approach for their constraints.

Quick Start

Use the attack-selection-guide skill to identify the optimal attack algorithms and transforms for your AI red teaming assessment of a custom LLM chatbot with strong content moderation defenses.

Frequently Asked Questions about attack-selection-guide

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

FAQPage Schema
How do I select the right adversarial attacks for an LLM red teaming assessment?▼

To select the right adversarial attacks for an LLM red teaming assessment, use a structured decision tree that matches attack algorithms and transforms to your specific target architecture, compute budget, and known defensive controls.

What is the best way to test jailbreaks against an AI system with strong content moderation?▼

The best way to test jailbreaks against an AI system with strong content moderation is to pair specialized attack algorithms like the pair attack with encoding transforms such as base64 to efficiently bypass defensive input sanitization.

Can I use this attack selection method for agentic systems and custom API endpoints?▼

Yes, you can use this attack selection method for agentic systems and custom API endpoints because it provides clear branching logic to map specific adversarial testing methods to diverse AI deployment types.

How do I map compute budgets to specific AI security testing algorithms?▼

You map compute budgets to specific AI security testing algorithms by evaluating available resources against the decision tree, which aligns recommended attack algorithms and parameter overrides with your operational constraints.

What threat categories are covered when selecting adversarial testing methods?▼

Selecting adversarial testing methods covers over 20 threat categories, including jailbreaks, MCP attacks, RAG poisoning, and data exfiltration testing, ensuring comprehensive security assessment coverage.

Related Skills

Explore More Software Engineering Skills→
AesopScottAesopScott

scaled-review

Adjust model tiers and processing depth based on finding severity.

Community
Advanced
EntroVyxEntroVyx
3

llm-prompt-injection

Test LLM endpoints for prompt injection vulnerabilities using Python scripts.

Community
Advanced
dreadnodedreadnode
11

workflow-patterns

Generate Python workflow templates for AI red teaming assessments via the Dreadnode Assessment API.

Official
Intermediate
DorianGalloDorianGallo
5

llm-prompt-injection

Identify and mitigate LLM prompt injection vulnerabilities across direct, indirect, and tool execution paths.

Community
Advanced