agentskillexchange Red-team agent workflows for jailbreaks, prompt injection, and policy failures with DeepTeam
Run local adversarial attack passes against agents, RAG pipelines, and chatbots to surface concrete failure classes before production rollout.
Prerequisites
Python environment, local or configured LLM access for chosen attacks
Installation
Use the upstream install or setup path that matches your environment:
- pip install -U deepteam
Requirements and caveats from upstream:
- 🔗 Run red teaming from the CLI with YAML configs, or programmatically in Python.
- DeepTeam does not require you to define what LLM system you are red teaming — because neither will malicious users. All you need to do is install deepteam, define a model_callback, and you're good to go.
- python
Basic usage or getting-started notes:
Getting Started |
📐 50+ ready-to-use vulnerabilities (all with explanations) powered by ANY LLM of your choice. Each vulnerability uses LLM-as-a-Judge metrics that run...
Red Team Your First LLM
Extracted from upstream docs: https://raw.githubusercontent.com/confident-ai/deepteam/HEAD/README.md