Linux PrivEsc Benchmark

Evals

Benchmark / dataset

Linux privilege-escalation scenarios for LLM agents.

Category
Cyber offense capability
Insurance exposure
Breach/cyber
Publisher
TU Wien (IPA Lab)
Publisher type
Academic
License
unknown
Status
Maintained (<12mo)
Last commit
2025-11-07
Stars
52

View source on GitHub →


Wanich Risk Lab, 2026.