hermes-jailbench
Jailbreak regression benchmark for LLM endpoints with repeatable known-pattern attacks and deterministic scoring
Paquete de plugins · de Hermes Labs
Resumen
hermes-jailbench es un paquete de plugins para herramientas de programación con IA publicado por Hermes Labs. Marketplaces que leemos y que lo publican: 1 (Community GitHub marketplaces). Lo vimos por primera vez el 2026-10-20 y desde entonces no hemos registrado cambios. Según nuestra pasada por los marketplaces del 2026-10-21.
Qué pide
- Se instala como paquete de plugins
Ninguno de los marketplaces que leemos publica sus herramientas ni los ajustes que pide.
Lo que declara, pide y ejecuta, completo
Instala solo plugins de desarrolladores en los que confíes. Mostramos lo que publican los marketplaces y no probamos plugins.
Funciona con
- Claude Code
Según los marketplaces que lo listan y el transporte MCP que declara, tal como lo documenta cada cliente. No probamos plugins.
Conectar
Comandos y configuraciones generados solo a partir de lo que declaran sus marketplaces. No los ejecutamos por ti ni probamos plugins.
Como plugin de Claude Code
Generado a partir de lo que declara Community GitHub marketplaces.
/plugin marketplace add hermes-labs-ai/hermes-jailbench
/plugin install hermes-jailbench@hermes-jailbenchDónde está publicado
| Marketplace | Estado | Versión | Cifras | Verificado | Visto por primera vez |
|---|---|---|---|---|---|
| Marketplace de la comunidad hermes-labs-ai/hermes-jailbench (Abrir el código en GitHub) | Publicado | 0.2.2 | Forks (GitHub): 3 Estrellas (GitHub): 12 |
Sin marca |
Cada cifra es del propio marketplace y nunca se suma entre marketplaces. Un marketplace que no publica cifras no muestra ninguna: sin número no es cero.
Figura en un marketplace de la comunidad
| Marketplace | Repositorio | Estrellas (GitHub) |
|---|---|---|
| hermes-jailbench | hermes-labs-ai/hermes-jailbench | 12 |
Qué contiene el paquete
Tal como se publica en Community GitHub marketplaces.
Skills: 1
hermes-jailbench
Qué cambió
- Pasó a ser un producto que seguimos
- Community GitHub marketplaces: apareció
Plugins similares
Productos cuyos propios nombres, descripciones, herramientas y skills son los más cercanos a este por su significado, en todos los marketplaces que leemos. La cercanía se ordena solo dentro de esta lista.
-
35-probe LLM/agent security red-team scan (injection, jailbreak, MCP abuse) with report.
-
AI threat modeling, prompt injection testing, and LLM security hardening.
-
synapse-audit io.github.digidenone/synapse-audit
AI-Powered Security Scanner for LLMs. Detects vulnerabilities and syncs with SynapseAudit.
-
mcp-server io.github.arkheiaai/mcp-server
Detect fabrication and hallucination in any LLM output. 30+ models supported.
-
mcp dev.safeprompt/mcp
Detect prompt injection, jailbreaks, and code injection in untrusted text before it reaches an LLM.
-
Paid remote MCP for LLM security scans, jailbreak checks, analytics, checkout, and readiness.
-
Prompt injection detection API for AI agents. Scan untrusted text before passing it to an LLM.
-
Prompt-injection detector for untrusted text before it reaches an LLM (RU/EN). BYO lovec.tech key.
-
Multi-agent LLM security layer detecting prompt injection and jailbreaks.
-
agentshield-mcp io.github.dl-eigenart/agentshield-mcp
Detect prompt injection, jailbreak, and social-engineering attacks in LLM agents.
Plugins similares por marketplace
La misma pregunta a cada marketplace por separado: ¿hay allí un equivalente de este plugin?
Publicado en Claude Code: claude-plugins-community (5)
-
VerifiedX helps Claude install and verify action protection in existing AI systems with minimal code changes. It inspects a repo, detects the smallest real integration seam such…
-
Skills to streamline adoption and usage of Giskard products (OSS, Hub, Guards) for testing, evaluating, and red-teaming AI agents.
-
Secure design patterns for Claude Code LLM applications: external content ingestion, endpoint hardening, output validation, system prompt design, and multi-agent action surface…
-
Use Claude Code without fear of data leakage. Unbound enforces command policies, DLP and jailbreak guardrails, and streams session analytics to your security dashboard — all with…
-
AI agent evaluation sandbox for Claude Code. Holdout scenario testing with Doer/Judge/Adversary/Observer roles, probabilistic satisfaction scoring, and append-only JSONL audit…
Publicado en Claude Code: claude-plugins-official (5)
-
Skills for adding DeepEval evaluations, tracing, datasets, Confident AI reports, and iterative improvement loops to AI applications.
-
Set up endorctl and use Endor Labs to scan, prioritize, and fix security risks across your software supply chain
-
Build, train, evaluate, and use open source AI models, datasets, and spaces.
-
Agent Skills for Together AI platform — inference, training, embeddings, audio, video, images, function calling, and infrastructure. Covers serverless chat completions…
-
Skills for working with Langfuse, the open-source LLM engineering platform for tracing, prompt management, and evaluation.
Publicado en Claude: knowledge-work-plugins (5)
-
Skills for working with Langfuse, the open-source LLM engineering platform for tracing, prompt management, and evaluation.
-
DataRobot skills for AI/ML workflows — model training, deployment, predictions, feature engineering, monitoring, explainability, data preparation, App Framework CI/CD, and…
-
Security review for Claude-generated code. Pattern-based warnings on edits, LLM-powered diff review on Stop, and an agentic commit reviewer that catches injection, XSS, SSRF…
-
The Vanta plugin connects Claude Code to Vanta's security and compliance platform through the Vanta MCP server. It combines Vanta's test-specific remediation intelligence with…
-
AI-first project auditor and re-engineer based on the 9 design principles and 7 design patterns from the TechWolf AI-First Bootcamp
Publicado en Codex: openai-curated (openai/plugins) (5)
-
Evaluate Codex skills and plugins from chat with a beginner-friendly start command, local-first reports, token budget explanations, and guided benchmarking.
-
Build with OpenAI APIs, Agents SDK, and ChatGPT Apps, and create and save OpenAI API keys from Codex.
-
Skills for NVIDIAs ecosystem spans GPU acceleration, CUDA, AI agents, inference, robotics, Physical AI, Omniverse, and simulation. This plugin helps you understand the pieces…
-
CrowdStrike Falcon Foundry development skills for building cybersecurity applications on the Falcon platform. Includes UI development, collections, functions, workflows, API…
-
Codex Security workflows for security scans, analysis, and investigation.
Publicado en Community GitHub marketplaces (5)
-
AI threat modeling, prompt injection testing, and LLM security hardening.
-
Decide, design, gate, judge, and defend evaluations for LLM, agent, and retrieval systems. Not ordinary unit tests.
-
Grounds answers about GenAI/LLM/agentic AI security in the OWASP GenAI Security Project's published research -- the LLM Top 10, the Agentic Top 10, Data Security risk/framework…
-
Configures and runs LLM evaluation using Promptfoo framework. Use when setting up prompt testing, creating evaluation configs (promptfooconfig.yaml), writing Python custom…
-
Checks every tool call, tool output and reply with TypeSafe's Jev model: prompt-injection screening, approval gating and secret scrubbing.
Publicado en Copilot CLI: github/awesome-copilot (5)
-
Run a lightweight, role-separated AI development team with flexible tools, developer-selected models, proportionate planning, and optional QA.
-
Three-layer verification pipeline for AI output. Extracts claims, finds sources, and flags hallucination risks so humans can verify before acting.
-
Phoenix AI observability skills for LLM application debugging, evaluation, and tracing. Includes CLI debugging tools, LLM evaluation workflows, and OpenInference tracing…
-
CrowdStrike Falcon Foundry development skills for building cybersecurity applications on the Falcon platform. Includes UI development, collections, functions, workflows, API…
-
Safe BLE diagnostics, evidence workflows, and guarded automation for AI agents.
Publicado en Copilot CLI: github/copilot-plugins (5)
-
Advanced Security plugin for GitHub Copilot.
-
Toolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
-
model-apps
Build and deploy Power Apps generative pages for model-driven apps with specialist agents for planning, entity creation, and parallel code generation. Requires PAC CLI >= 2.7.0…
-
Build and manage Microsoft Dataverse solutions using natural language. Includes table/column creation, solution lifecycle, data operations, and MCP server configuration.
-
Bring Azure DevOps work-item, repository, and pull-request workflows into GitHub Copilot.
Publicado en Cursor: cursor/plugins (5)
-
Iterative self-referential AI loops using the Ralph Wiggum technique.
-
CLI-backed repo compatibility scans plus agents that audit startup, validation, and docs against reality.
-
if you want to go fast, go deep first. pstack helps you write less, but higher quality code. rigorous agent workflows you can parallelize with confidence.
-
Fan large tasks out across parallel cloud agents with planners, workers, verifiers, and structured handoffs.
-
playwright-mcp io.github.microsoft/playwright-mcp
Playwright Tools for MCP
Publicado en Docker MCP Catalog (5)
-
Read and score Opik traces, experiments, datasets and prompts from your AI assistant.
-
Bridges multiple AI models and CLIs, enabling orchestrated workflows across Claude Code, Gemini CLI, Codex CLI, and other AI development tools.
-
Discovers and retrieves llms.txt from websites.
-
Provides tools to search and retrieve Google Gemini API documentation.
-
Tools for interacting with Hugging Face models, datasets, research papers, and more.
Publicado en Official MCP Registry (5)
-
35-probe LLM/agent security red-team scan (injection, jailbreak, MCP abuse) with report.
-
synapse-audit io.github.digidenone/synapse-audit
AI-Powered Security Scanner for LLMs. Detects vulnerabilities and syncs with SynapseAudit.
-
mcp-server io.github.arkheiaai/mcp-server
Detect fabrication and hallucination in any LLM output. 30+ models supported.
-
mcp dev.safeprompt/mcp
Detect prompt injection, jailbreaks, and code injection in untrusted text before it reaches an LLM.
-
Paid remote MCP for LLM security scans, jailbreak checks, analytics, checkout, and readiness.
Publicado en npm registry (MCP servers) (5)
-
mcp com.dechonet/mcp
30 security tools for AI agents: phishing links, exposure maps, DNS, SSL, PQC, history, pivots.
-
Evidence-backed crypto due diligence with sources, freshness, and a runtime receipt on every call.
-
One workspace for every AI coding assistant. Shared tasks, memory, and governance.
-
Human-in-the-loop for AI agents over MCP elicitation: confirm/form dialogs plus a capability doctor
-
guardvibe io.github.goklab/guardvibe
Deterministic security layer your AI can't be. 611 rules, 39 tools, CLI + doctor + host audit.
Encontrados por significado, no por código ni repositorio compartidos: los plugins similares siguen siendo productos distintos, y esto no es una reseña ni una recomendación.
¿Quieres esta marca para tu plugin en nuestro catálogo?
Demuestra que lo mantienes con un archivo en su repositorio, un archivo en tu dominio o un registro DNS, y podrás mostrar esta marca en la ficha, con banners en vivo para tu web y tu README. Cómo funciona la verificación
Además recibirás avisos cuando un marketplace lo publique, lo retire, cambie su marca verificada o lo que pide, y su endpoint remoto quedará monitorizado como un servicio web.
Datos de Community GitHub marketplaces. Las cifras proceden de nuestros propios recorridos periódicos por los marketplaces, leída por última vez el . No publicamos datos de contacto de los editores de plugins.