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

transform-reference

Catalog all 183 AIRT SDK transforms with names, parameters, and LLM requirements.

11|1|Updated May 4, 2026
Search Tags:#security testing#ai red teaming#transform catalog#airt sdk#attack payloads#transform lookup
One-click install
npx skills add https://github.com/dreadnode/capabilities --skill transform-reference
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: transform-reference
Source: https://github.com/dreadnode/capabilities/tree/main/capabilities/ai-red-teaming/skills/transform-reference
Command: npx skills add https://github.com/dreadnode/capabilities --skill transform-reference

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill eliminates the guesswork and errors that come with trying to remember or guess transform names and parameters for the AIRT SDK, providing a single authoritative reference for all 183 available transforms used in AI red teaming workflows.

Core Features & Use Cases

  • Comprehensive Transform Catalog: Lists every official transform across 20+ categories including encoding, ciphers, persuasion, injection attacks, exfiltration, and multi-agent attacks, with exact names, required parameters, and LLM usage requirements.
  • Goal-Based Selection Guide: Includes curated tables of recommended transforms for common red teaming objectives like content filter bypass, system prompt extraction, MCP security testing, and RAG poisoning.
  • Use Case: Red teamers and security researchers can use this reference to quickly validate transform names and parameters when configuring attack payloads via the generate_attack or generate_agentic_attack tools, avoiding invalid configurations that would fail during execution.

Quick Start

Use the transform-reference skill to look up the exact name and LLM requirement for the authority_appeal persuasion transform.

Frequently Asked Questions about transform-reference

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

FAQPage Schema
What are AI red teaming transforms and when do I need them?▼

AI red teaming transforms are payload modification operations across categories like encoding, ciphers, persuasion, and injection attacks. You need them when configuring attack payloads via the AIRT SDK to test security vulnerabilities.

How do I find the exact name and parameters for an AIRT SDK transform?▼

To find exact transform names and parameters for the AIRT SDK, use the transform-reference catalog, which lists all 183 official transforms with their required parameters and LLM usage requirements.

Which transforms are best for bypassing content filters or extracting system prompts?▼

For content filter bypass or system prompt extraction, use the goal-based selection guide within the transform catalog, which recommends specific transforms for common red teaming objectives like RAG poisoning and MCP security testing.

Do AIRT SDK transforms require an LLM to execute?▼

Some AIRT SDK transforms require an LLM to execute, while others do not. The transform catalog explicitly lists the LLM usage requirements for each of the 183 available transforms to help you avoid invalid configurations.

Why does my generate_attack configuration fail with an invalid transform error?▼

Your generate_attack configuration fails because of invalid transform names or parameters. Use the authoritative transform catalog to validate exact names and parameters before configuring attack payloads to avoid execution failures.

What categories of attack payloads are available for AI red teaming?▼

Available attack payload categories include encoding, ciphers, persuasion, injection attacks, exfiltration, and multi-agent attacks, encompassing all 183 official AIRT SDK transforms across 20 plus distinct categories.

Related Skills

Explore More Software Engineering Skills→
atlanhqatlanhq
4

atlan-cli-install-configure

Install the Atlan CLI only when missing and configure tenant authentication.

Official
Advanced
dreadnodedreadnode
11

trace-analysis-advisor

Analyze historical OTEL trace data to recommend attack strategies for AI red teaming.

Official
Advanced
chrismcmackenchrismcmacken

review-artifacts

Triage artifact scan results to surface reportable bug bounty findings.

Community
Intermediate
dreadnodedreadnode
11

error-troubleshooting

Diagnose and resolve common errors in AI red teaming workflows.

Official
Intermediate