Red Team Agent Workflows For Jailbreaks Prompt Injection And Pol

---
title: "Red-team agent workflows for jailbreaks, prompt injection, and policy failures with DeepTeam"
description: "Run local adversarial attack passes against agents, RAG pipelines, and chatbots to surface concrete failure classes before production rollout."
verification: "listed"
source: "https://github.com/confident-ai/deepteam"
author: "Confident AI"
publisher_type: "organization"
category:
  - "Security & Verification"
framework:
  - "Multi-Framework"
tool_ecosystem:
  github_repo: "confident-ai/deepteam"
  github_stars: 1566
---

# 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

Choose whichever fits your setup:

1. Copy this skill folder into your local skills directory.
2. Clone the repo and symlink or copy the skill into your agent workspace.
3. Add the repo as a git submodule if you manage shared skills centrally.
4. Install it through your internal provisioning or packaging workflow.
5. Download the folder directly from GitHub and place it in your skills collection.

Install command or upstream instructions:

```
Follow the repository quickstart to install DeepTeam, configure the model or local runtime you want to use for attack generation and judging, then run red-team passes against the target agent or LLM system and review the reported failures.
```

## Documentation

- https://github.com/confident-ai/deepteam

## Source

- [Agent Skill Exchange](https://agentskillexchange.com/skills/red-team-agent-workflows-for-jailbreaks-prompt-injection-and-policy-failures-with-deepteam/)