AgentDojo vs PromptRAID
AgentDojo
agentdojo.spylab.aiPromptRAID
github.comSide by side
| Figure | AgentDojo | PromptRAID |
|---|---|---|
| Price from | — | — |
| Free plan | — | — |
| Free trial | — | — |
| Open source | — | — |
| Windows | — | Yes |
| Linux | Yes | Yes |
| API | Yes | — |
| Self-hosted | Yes | — |
| Plans published | 0 | 0 |
| Spec score · AI Security Testing Tools | 7.8 (#12) | 7.0 (#23) |
| License | The project's GitHub page identifies its license as MIT. | PromptRAID is distributed under the MIT License, which permits use, copying, modification, distribution, sublicensing, and sale subject to its terms. |
| Model providers | Documented tool-calling LLM implementations support OpenAI, Anthropic, Google, and Cohere; the docs also describe using Llama 3 70B through TogetherAI’s API. | The harness supports Anthropic, Gemini, Groq, Cerebras, and OpenRouter, including OpenAI-compatible endpoints. |
| Purpose | AgentDojo is a dynamic environment for evaluating prompt injection attacks and defenses for LLM agents. | PromptRAID is an automated prompt injection red-teaming framework for LLM-based agents, mapped to MITRE ATLAS. |
In their own words
AgentDojo
AgentDojo has no write-up on Specifiction yet; its figures are above.