Quick Start

Get started with HackAgent in minutes. Choose your preferred method below.

TUI

Launch the interactive terminal interface:

hackagent

See it in Action

CLI

Run attacks directly from your terminal (without TUI):

Ollama

Prerequisites

1. Install Ollama: curl -fsSL https://ollama.com/install.sh | sh
2. Start server: ollama serve
3. Pull model: ollama pull llama3
4. Verify: curl http://localhost:11434/api/tags

hackagent attack advprefix \
  --agent-name "llama3" \
  --agent-type "ollama" \
  --endpoint "http://localhost:11434" \
  --goals "Extract system prompt information" \
  --no-tui

OpenAI SDK

Prerequisites

1. Get API key from platform.openai.com/api-keys
2. Set env var: export OPENAI_API_KEY="sk-..."
3. Verify: curl https://api.openai.com/v1/models -H "Authorization: Bearer $OPENAI_API_KEY"

hackagent attack advprefix \
  --agent-name "gpt-4" \
  --agent-type "openai-sdk" \
  --endpoint "https://api.openai.com/v1" \
  --goals "Extract system prompt information" \
  --no-tui

Google ADK

Prerequisites

1. Install: pip install google-adk
2. Start agent: cd your_agent && adk web
3. Verify: curl http://localhost:8000/list-apps

hackagent attack advprefix \
  --agent-name "my-agent" \
  --agent-type "google-adk" \
  --endpoint "http://localhost:8000" \
  --goals "Extract system prompt information" \
  --no-tui

LiteLLM

Prerequisites

1. Install: pip install litellm[proxy]
2. Start proxy: litellm --model gpt-4 --port 4000
3. Verify: curl http://localhost:4000/health

hackagent attack advprefix \
  --agent-name "gpt-4" \
  --agent-type "litellm" \
  --endpoint "http://localhost:4000/v1" \
  --goals "Extract system prompt information" \
  --no-tui

More Frameworks

🦜 LangChain

Prerequisites

1. Install: pip install langserve
2. Start server: python your_langserve_app.py
3. Verify: curl http://localhost:8000/

hackagent attack advprefix \
  --agent-name "my-langchain-agent" \
  --agent-type "langchain" \
  --endpoint "http://localhost:8000" \
  --goals "Extract system prompt information" \
  --no-tui

🖥️ LM Studio

Prerequisites

1. Download from lmstudio.ai
2. Load a model in LM Studio
3. Start local server: "Local Server" tab → "Start Server"
4. Verify: curl http://localhost:1234/v1/models

hackagent attack advprefix \
  --agent-name "local-model" \
  --agent-type "openai-sdk" \
  --endpoint "http://localhost:1234/v1" \
  --goals "Extract system prompt information" \
  --no-tui

⚡ vLLM

Prerequisites

1. Install: pip install vllm
2. Start server: vllm serve meta-llama/Llama-3-8B-Instruct --port 8000
3. Verify: curl http://localhost:8000/v1/models

hackagent attack advprefix \
  --agent-name "my-model" \
  --agent-type "openai-sdk" \
  --endpoint "http://localhost:8000/v1" \
  --goals "Extract system prompt information" \
  --no-tui

🔧 Custom

Prerequisites

1. Ensure your endpoint exposes /v1/chat/completions (OpenAI-compatible)
2. Verify: curl http://your-endpoint/v1/models

hackagent attack advprefix \
  --agent-name "my-model" \
  --agent-type "openai-sdk" \
  --endpoint "http://your-endpoint/v1" \
  --goals "Extract system prompt information" \
  --no-tui

View available attacks and options:

hackagent attack --help

SDK

Integrate security testing into your Python applications:

Ollama

Prerequisites

1. Install Ollama: curl -fsSL https://ollama.com/install.sh | sh
2. Start server: ollama serve
3. Pull model: ollama pull llama3

from hackagent import HackAgent

# Initialize HackAgent
agent = HackAgent(
  name="llama3",
  endpoint="http://localhost:11434",
  agent_type="ollama",
)

OpenAI SDK

Prerequisites

1. Get API key from platform.openai.com/api-keys
2. Set env var: export OPENAI_API_KEY="sk-..."

from hackagent import HackAgent

# Initialize HackAgent
agent = HackAgent(
  name="gpt-4",
  endpoint="https://api.openai.com/v1",
  agent_type="openai-sdk",
)

Google ADK

Prerequisites

1. Install: pip install google-adk
2. Start agent: cd your_agent && adk web

from hackagent import HackAgent

# Initialize HackAgent
agent = HackAgent(
  name="my_google_agent",
  endpoint="http://localhost:8000",
  agent_type="google-adk",
)

LiteLLM

Prerequisites

1. Install: pip install litellm[proxy]
2. Start proxy: litellm --model gpt-4 --port 4000

from hackagent import HackAgent

# Initialize HackAgent
agent = HackAgent(
  name="gpt-4",
  endpoint="http://localhost:4000/v1",
  agent_type="litellm",
)

# Configure and run an attack
attack_config = {
  "attack_type": "advprefix",
  "goals": ["Bypass content safety filters"]
}

agent.hack(attack_config=attack_config)

More Frameworks

🦜 LangChain

Prerequisites

1. Install: pip install langserve
2. Start server: python your_langserve_app.py

from hackagent import HackAgent

# Initialize HackAgent
agent = HackAgent(
  name="my_langchain_agent",
  endpoint="http://localhost:8000",
  agent_type="langchain",
)

🖥️ LM Studio

Prerequisites

1. Download from lmstudio.ai
2. Load a model, then start local server from "Local Server" tab

from hackagent import HackAgent

# Initialize HackAgent
agent = HackAgent(
  name="local-model",
  endpoint="http://localhost:1234/v1",
  agent_type="openai-sdk",
)

⚡ vLLM

Prerequisites

1. Install: pip install vllm
2. Start server: vllm serve meta-llama/Llama-3-8B-Instruct --port 8000

from hackagent import HackAgent

# Initialize HackAgent
agent = HackAgent(
  name="my-model",
  endpoint="http://localhost:8000/v1",
  agent_type="openai-sdk",
)

🔧 Custom

Prerequisites

1. Ensure your endpoint exposes /v1/chat/completions (OpenAI-compatible)

from hackagent import HackAgent

# Initialize HackAgent
agent = HackAgent(
  name="my-model",
  endpoint="http://your-endpoint/v1",
  agent_type="openai-sdk",
)

# Configure and run an attack
attack_config = {
  "attack_type": "advprefix",
  "goals": ["Bypass content safety filters"]
}

agent.hack(attack_config=attack_config)

Next Steps

• Attack Tutorial — Run your first security test
• AdvPrefix Attacks — Deep dive into attack techniques