Hacktoberfest 2026: le issue che i maintainer hanno segnato per ottobre, aperte e adatte ai principianti. Sfoglia le issue Hacktoberfest

[External Plugin]: hermes-jailbench

Aperta
#3,307 2 commenti 0 reazioni 0 assegnatari Vedi su GitHub

Nessuno ha ancora preso questa issue.

Valutazione

Difficoltà
3/5
Tempo stimato
1-2 giorni
Idoneità per principianti
48/100
Tipo di issue
Funzionalità
Chiarezza
Abbastanza chiara
Stato di attività
Attiva
Stack tecnologico
github
Ambito
ai, devtools, security

Direzione di ricerca

Start by reviewing the pinned commit ec933be5e4c9f8c07caa0c9f19b45a925067d655 in hermes-labs-ai/hermes-jailbench and compare its submission details with the repository's contribution, security, and responsible AI policies. Check the referenced .claude-plugin/marketplace.json entry and verify that the plugin is suitable for inclusion; done means the review is complete and any required marketplace update is identified.

Scritto dal modello di indicizzazione a partire dal testo della issue.

Descrizione

external-plugin needs-review:HIGH ready-for-review
Plugin name

hermes-jailbench

Short description

Jailbreak regression benchmark for LLM endpoints with repeatable known-pattern attacks and deterministic scoring.

GitHub repository

hermes-labs-ai/hermes-jailbench

Plugin path inside the repository

No response

Ref to review

No response

Commit SHA to review

ec933be5e4c9f8c07caa0c9f19b45a925067d655

Version

0.2.1

License identifier

MIT

Author name

Hermes Labs

Author URL

https://github.com/hermes-labs-ai

Homepage URL

https://github.com/hermes-labs-ai/hermes-jailbench

Keywords

security, red-teaming, llm-security, benchmark, evaluation, developer-tools

Additional notes for reviewers

This is a defensive regression-testing tool: it runs a fixed corpus of publicly known jailbreak patterns against an LLM endpoint the user already controls or is authorized to test, and produces deterministic pass/fail scoring so a team can track whether their own safety mitigations regress between releases. It does not discover novel attacks, target third-party services, or exfiltrate data. Listed in the Hermes Labs Copilot marketplace manifest (https://github.com/hermes-labs-ai/copilot-plugins/blob/main/.claude-plugin/marketplace.json) as a root url source, tracking the main branch. The commit SHA above is main's HEAD at submission time, pinned here for immutable review. Submitted by the plugin's own maintainer (Hermes Labs).

Submission checklist
  • The plugin lives in a public GitHub repository.
  • The ref and/or sha I provided is immutable (release tag and/or full 40-character commit SHA), not a branch.
  • This submission follows this repository's contribution, security, and responsible AI policies.
  • This plugin is not already listed in the Awesome Copilot marketplace.
Lingua principale
JavaScript
Stelle
39.2k
Fork
5k
Merge medio
1g 18h
PR unite (30g)
114

Guida per i contributori

Apri la guida per i contributori

Come iniziare

  1. Leggi tutta la issue e poi la guida ai contributi del progetto.
  2. Commenta sulla issue per dire che te ne occupi tu — evita che due persone facciano lo stesso lavoro.
  3. Fai un fork del repository e lavora su un branch.
  4. Apri una pull request che faccia riferimento al numero della issue.

Altre issue di github/awesome-copilot

Tutte le issue di github/awesome-copilot

Issue simili

Altre issue su JavaScript

Ricevi le nuove issue nella tua casella

Un breve riepilogo di issue GitHub adatte ai principianti.