Agent DOJO RL Env (Prime Intellect)

Fresh

Benchmark for agent robustness against prompt injection attacks in tool-use scenarios

Type: RL Env
Publisher: Prime Intellect
Tags: Tool Use Security Adversarial Prompt Injection
Runtime: multi-turn
License: unknown
Size: v0.1.0
Published: Nov 2025
Canonical: app.primeintellect.ai/dashboard/environments/primeintellect/agent-dojo

Cite

Notes

Only stored in your browser.

Attribution

README: api.primeintellect.ai/api/v1/environmentshub/primeintellect/agent-dojo/@0.1.0/inspect

Attribution policy →

Lift evidence

1

Eval	Tools known to lift	Source paper
AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents	Agent DOJO RL Env (Prime Intellect)	-