LLM Redteam Overview

LLM Red Team Skill Catalog — AATMF v3

This is the routing skill for AI/LLM red-team work. The 15 sub-skills below cover every tactic in the AI/ML Adversarial Tactics, Techniques & Mitigations Framework (AATMF v3). Load the specific sub-skill that matches the attacker objective.

Tactic Map

Quick Routing

Target type identified?
├── Chat-only LLM endpoint     → T01, T02, T03, T10
├── LLM with tools / function calling → T05, T11
├── LLM with RAG / retrieval     → T12, T01 (indirect)
├── LLM with multimodal input    → T09
├── Fine-tuned / custom model    → T06, T10 (extraction)
├── Cross-tenant / shared infra  → T14, T13
└── Human-in-the-loop product    → T15, T08

Tooling

Cross-Reference

• MITRE ATLAS — covers tactic-level coverage (Reconnaissance → Impact). AATMF is more attacker-procedure focused. Most AATMF techniques map to one or more ATLAS techniques; the sub-skills note the mapping in their frontmatter.
• OWASP LLM Top 10 — risk-class level. AATMF tactics map across LLM01-LLM10.
• NIST AI RMF AI 600-1 — governance lens; AATMF gives the offensive counterpart.

When in doubt

If the target's surface or behavior doesn't cleanly match one tactic, run a T01 + T05 probe first — direct prompt injection and function-call abuse are the most common, highest-yield starting points and their results inform which other tactics are reachable.