# Stress-test agent defenses with AgentDojo

> Run AgentDojo benchmark environments to evaluate prompt-injection attacks and defenses against LLM agents before trusting them with real tools or data.

- Skill: `agentskillexchange/stress-test-agent-defenses-with-agentdojo` (Agent Skill)
- Install (CLI): `npx skillmds@latest add agentskillexchange/stress-test-agent-defenses-with-agentdojo`
- Raw SKILL.md: https://api.skillmd.com/api/skills/agentskillexchange/stress-test-agent-defenses-with-agentdojo/raw
- Safety review: pending (external: skill-scanner PASS, skillspector CAUTION)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: agentskillexchange (https://skillmd.com/u/agentskillexchange)
- Updated: 2026-09-08
- Page: https://skillmd.com/skills/agentskillexchange/stress-test-agent-defenses-with-agentdojo

---


# Stress-test agent defenses with AgentDojo

Run AgentDojo benchmark environments to evaluate prompt-injection attacks and defenses against LLM agents before trusting them with real tools or data.

## Prerequisites

Python 3.10+, agentdojo package, model provider credentials for the target pipeline, optional transformers extra for prompt-injection detector workflows

## Installation

Use the upstream install or setup path that matches your environment:
- pip install agentdojo
- pip install "agentdojo[transformers]"

Requirements and caveats from upstream:
- ![PyPI - Python Version](https://img.shields.io/pypi/pyversions/agentdojo) ![PyPI - Downloads](https://img.shields.io/pypi/dm/agentdojo) ![PyPI - Version](https://img.shields.io/pypi/v/agentdojo)
- python -m agentdojo.scripts.benchmark -s workspace -ut user_task_0 \
- python -m agentdojo.scripts.benchmark --model gpt-4o-2024-05-13 \

Basic usage or getting-started notes:
- [!IMPORTANT]
- Note that the API of the package is still under development and might change in the future.
- If you want to use the prompt injection detector, you need to install the transformers extra:

- Source: https://github.com/ethz-spylab/agentdojo
- Extracted from upstream docs: https://raw.githubusercontent.com/ethz-spylab/agentdojo/HEAD/README.md

## Documentation

- https://agentdojo.spylab.ai/

## Source

- [Agent Skill Exchange](https://agentskillexchange.com/skills/stress-test-agent-defenses-with-agentdojo/)