# hermes-labs-ai/hermes-jailbench

Zero-LLM deterministic jailbreak regression benchmark: runs a repeatable battery of known-pattern attacks against an LLM endpoint and scores refusal/partial/compliance across runs. Catch when a model or prompt update silently got weaker. Single-turn, responsible-use. pip install hermes-jailbench

## Repository

- [Catalog detail page](https://awesomeclaudeplugins.com/hermes-labs-ai/hermes-jailbench)
- [GitHub repository](https://github.com/hermes-labs-ai/hermes-jailbench)
- Stars: 4
- Forks: 2
- 1 plugin entries are reported.

## Catalog provenance

- Publication state: indexable
- Quality note: Canonical repository has a description and validated plugin count.
- Catalog snapshot: Sep 19, 2026
- Repository metadata source: public GitHub API when available

## Installation

When this repository exposes a Claude Code marketplace, add it with:

```bash
/plugin marketplace add hermes-labs-ai/hermes-jailbench
```