Apps · PROJECT NOTES
AgentDojo
A tool-use evaluation environment with simulated applications and untrusted tool data, designed to measure task utility and resistance to prompt injection.
What can you do with it?
Compare agent defenses while checking whether legitimate tool-based tasks still succeed.
What should you know before using it?
A specialized security and utility benchmark using simulated app tools, not native banking or workplace software. Requires Python 3.10+ and model-provider configuration. Package APIs are still evolving. Code is MIT-licensed.
What is verified here?
This entry was reviewed against original project material. We have not independently run the software or reproduced its results. AI-development claims are author-reported; check upstream for current versions, setup requirements, and licenses.
- Resource type
- Environment + benchmark
- Provenance
- Development provenance not established
- Reviewed
- Platforms
- Consult upstream documentation