Script Kitty OS

All

2 repositories

HolyTrinity-Benchmark
Public
Adversarial security benchmark for agent authorization: does a compromised agent's policy-violating proposal become an unauthorized external effect? 73 trials, …
elixir reproducible-research beam
elixir reproducible-research beam authorization ai-safety ai-security ablation-study llm-agents agent-security adversarial-evaluation
Elixir
•
Other
•2•6•1•0•Updated Aug 31, 2026Aug 31, 2026
.github
Public
0•0•0•0•Updated Aug 28, 2026Aug 28, 2026

ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.