← all datasets
◆ Evals & benchmarks · Prompt injection & jailbreaks
AgentDojo
MITA benchmark of agent tasks with embedded prompt-injection attacks, measuring both task success and attack success.
Summary
- Formats
python- License
- MIT
- Added
- 2026-09-10
Get it
From the project’s own instructions where it documents any; otherwise a plain clone.
-
$ pip install agentdojo
Add the transformers extra (agentdojo[transformers]) for the prompt-injection detector.
Contents
36,860 files 37.8 MB repository
-
.json36,680 -
.py122 -
.md24 -
.yaml17 -
(no ext)6 -
.sh3 -
.ipynb2 -
.bib1
Use it with
Commands are curated, not yet run by us.
Inspect AI — Run an Inspect task file; the benchmark has to be wrapped as an Inspect task first.
$ inspect eval task.py --model openai/gpt-4o-mini