InnerVault

hermes-jailbench

Stale GitHub, hermes-labs-ai

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

Open the source (opens github.com) https://github.com/hermes-labs-ai/hermes-jailbench

What it is

Skills from hermes-labs-ai.

The problem it solves and who it suits haven't been reviewed by InnerVault. The description above is the source's own.

How to get it

Get the code

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

Standard git access to a public repository

Setup steps: not provided by the source. Follow the instructions on the source.

Related

  1. 5,660 AI security links: prompt injection, LLM & AI agent security, MCP, coding agents, agent skills & supply chain, red teaming, guardrails, sandboxing, incidents & CVEs, governance. 570 arXiv papers, 1,155 GitHub repos, 570 X posts, 29 categories of plain markdown you can grep, diff and fork. Obsidian vault export. Added, not endorsed.

    Stale GitHub, AnthonyHerman 8 ★CC-BY-4.0Updated 5 days ago

    git clone https://github.com/AnthonyHerman/ai-security-corpus.git
  2. hermeneutic

    Skills

    Turn corrections from AI agent logs into guidance for similar tasks. Local memory with semantic retrieval, prompt-context hooks, and response checks.

    Stale GitHub, hermes-labs-ai 9 ★Apache-2.0Updated 27 days ago

    git clone https://github.com/hermes-labs-ai/hermeneutic.git
  3. skillguard

    Skills

    Security scanner for AI agent skills. Detects prompt injection, data exfiltration, and malicious payloads before you install.

    Stale GitHub, obielin 20 ★Custom licence (see repository)Updated 24 days ago

    git clone https://github.com/obielin/skillguard.git
  4. Anthropic's public collection of agent skills, including the document skills behind Claude's Word, PDF, PowerPoint and Excel features.

    Hand-checked InnerVault (hand-checked), Anthropic 188.2k ★Mixed: most skills Apache-2.0; the document skills are source-available, not…

    /plugin marketplace add anthropics/skills
  5. instar

    Skills

    Persistent Claude Code agents with scheduling, sessions, memory, and Telegram.

    Indexed GitHub, JKHeadley 86 ★MITUpdated today

    git clone https://github.com/JKHeadley/instar.git
  6. AI agents now operate with authority. Authority without discipline is how complex systems fail. Nuclear’s control loop, ported to AI-assisted software engineering.

    Stale GitHub, FlyFission 33 ★MITUpdated 19 days ago

    git clone https://github.com/FlyFission/nuclear-grade-context-engineering.git