Share your thoughts, 1 month free Claude Pro on usSee more

Home/Benchmarks

Authorization on Progent adversarial

23.33UAR

Progent adversarial

Updated 14d ago

Evaluation Results

Method	Links
Progent adversarial 2026.05		23.33

SOTA Paper

Progent adversarial

Progent: Securing AI Agents with Privilege Control

Dataset

Progent

Follow for update

@wizwand_team Discord

Related Benchmarks

Authorization on Oracle-certificate traces HACR Audit on Multi-Agent Benchmark Suite (AgentDojo, AgentDyn, SafeToolBench, VPIBench, VisualWebArena, DocVQA 500)Agent Safety Evaluation on AgentDojo Agent Safety Evaluation on AgentDyn Agent Safety Evaluation on DocVQA

© 2026 wizwand

Blog Contact Changelog Swarm

Privacy Policy Terms of Service FAQs Swarm Docs