Agent DOJO RL Env (Prime Community)

Fresh

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

Type: RL Env
Publisher: Prime Community
Tags: Tool Use Security Adversarial Prompt Injection
Runtime: multi-turn
License: unknown
Size: v0.1.0
Published: Mar 2026
Canonical: app.primeintellect.ai/dashboard/environments/prime-community/agent-dojo

Cite

Notes

Only stored in your browser.

Attribution

Public scores on this env

2 vf-eval reports across 2 models

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 Community)	-