Trial Benchmark Defense
AgentDojo
AgentDojo is a Python benchmark and dynamic environment for measuring prompt injection attacks and defenses against tool-using LLM agents across task suites such as workspace. It is used by researchers and developers to score agent utility and attack success under configurable defenses and attacks.
Worth piloting on a real project; expect some rough edges.
Facts
- Repository
- ethz-spylab/agentdojo
- Homepage
- github.com
- Listed via
- Curated
- First seen
- 2026-11-08
- License
- MIT
- Stars
- 1,065
- Last commit
- 2026-06-02
- Latest release
- v0.1.35 · 2025-10-27
- Checked
- 2026-11-22
Techniques
Listing is not endorsement. Summaries and notes are AI-assisted and reviewed; repository facts refresh automatically.