Skip to content
@ScriptKittyOS

Script Kitty OS

Popular repositories Loading

  1. HolyTrinity-Benchmark HolyTrinity-Benchmark Public

    Adversarial security benchmark for agent authorization: does a compromised agent's policy-violating proposal become an unauthorized external effect? 73 trials, nine families, an independent oracle,…

    Elixir 5 1

Repositories

Showing 1 of 1 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, nine families, an independent oracle, per-mechanism ablation, confidence intervals. 0 unauthorized effects in 61 attack trials (95% CI [0.0%, 5.9%]). Reproduction is partial.

    ScriptKittyOS/HolyTrinity-Benchmark's past year of commit activity
    Elixir 5 1 1 0 Updated Aug 4, 2026

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Loading…

Most used topics

Loading…