RedTeamCUA

Evals

Benchmark / dataset

Adversarial testing of computer-use agents in hybrid web-OS envs.

Category
Prompt injection & agent security
Insurance exposure
Agent actions
Publisher
Ohio State
Publisher type
Academic
License
Apache-2.0
Status
Maintained (<12mo)
Last commit
2026-02-09
Stars
65

View source on GitHub →

Wanich Risk Lab, 2026.