AI Red Team Prompt Pack: 100 LLM Attack Prompts for Security Testing

AI Red Team Labs — Thu, 16 Jul 2026 18:56:25 +0000

What Is This?

The AI Red Team Prompt Pack v1.0 is a curated collection of 100 battle-tested LLM attack prompts across 18 categories, built for security researchers and AI red teamers.

Who Is This For?

AI security researchers
Red teamers evaluating LLM deployments
Developers building safety guardrails
Bug bounty hunters targeting AI systems

Why $29?

At $29, it's less than an hour of consulting time and saves weeks of prompt research. Every prompt has been tested against GPT-4, Claude, Gemini, and Llama.

Get It

AI Red Team Prompt Pack v1.0 — $29

100 prompts. 18 categories. Start breaking LLMs today.

The LLM Red Teamer's Toolkit: 18 Attack Categories Every AI Security Engineer Should Know

AI Red Team Labs — Thu, 16 Jul 2026 17:22:41 +0000

LLM security red teaming is one of the fastest-evolving areas in cybersecurity. After months of hands-on testing across GPT-4, Claude, Gemini, and open-source models, here are the 18 attack categories every AI security engineer should know.

1. Direct Prompt Injection

Attacker embeds instructions in user input to override the system prompt. Still the most common LLM vulnerability.

2. Indirect Prompt Injection

Malicious instructions hidden in content the LLM processes (web pages, docs, emails). The LLM executes attacker instructions from third-party data.

3. Jailbreak Attacks

Persona hijacking, DAN variants, roleplay escalation. Models resist single-shot attempts but often cave to creative framing.

4. System Prompt Extraction

Getting the model to reveal its hidden system prompt, exposing business logic and internal instructions.

5. Multi-Turn Manipulation

Conversational priming across 3-7 turns to gradually shift the model's context and safety posture.

6. Context Window Poisoning

Flooding the context with adversarial content to dilute safety instructions.

7. Token Smuggling & Encoding Bypasses

Base64, leetspeak, unicode substitution. Safety filters miss encoded payloads constantly.

8. Goal Hijacking

Redirecting an LLM agent from its intended task to an attacker-specified objective.

9. Instruction Override

Inputs that cause the model to prioritize attacker instructions over system-level directives.

10. Data Exfiltration via LLM

Using LLM agents to extract sensitive data from connected systems.

11-18: Advanced Categories

Memory & Embedding Poisoning, Model Denial of Service, Adversarial Suffix Attacks, Constitutional AI Bypasses, Multi-Modal Injection, Agent Task Hijacking, Supply Chain Prompt Attacks, and Alignment Probing.

I've compiled 100 adversarial prompts across these 18 categories, each with severity rating, attack goal, expected vulnerable response, and detection indicator, into a structured PDF: AI Red Team Prompt Pack v1.0

What attack vectors are you seeing most in production LLM systems? Happy to discuss in the comments.

DEV Community: AI Red Team Labs