agentsh

agentsh Nota para macOS: La aplicación nativa de enforcement en macOS mediante ESF Endpoint Security Framework + NE Network Extension está en Alpha. Funciona de extremo a extremo: los eventos de archivos, procesos y red fluyen a través de la extensión del sistema hasta el motor de políticas Go,...

agent-governance-toolkit

🌍 English | 日本語 | 简体中文 | 한국어 Kit de Herramientas de Gobernanza de Agentes Lleva agentes a producción sin perder el sueño 🚀Inicio Rápido · 📋 Especificaciones · 📦 PyPI · 📝 Registro de Cambios -brightgreen !ATFhttps://img.shields.io/badge/ATF-All5Elements-b...

kontext-cli

Sitio web | Documentación | Dashboard | Discord Kontext es una plataforma de autorización para agentes de IA. Ayuda a los equipos a controlar a qué pueden acceder los agentes y qué pueden hacer mediante credenciales con alcance, aplicación de políticas, aprobaciones y registros de auditoría...

cupcake

Cupcake Haz que los agentes de IA sigan las reglas. Capa de aplicación de políticas para agentes de IA; ofrece un mejor rendimiento y seguridad sin consumir contexto del modelo. Cumplimiento determinista de reglas para tus agentes. Ejemplos interactivos Mejor rendimiento al sacar las reglas del...

Boucle-framework

Boucle Claude Code hooks that actually enforce your rules. 7 standalone hooks, plus enforce-hooks for CLAUDE.md policy, audit tooling, 1,900+ tests, and a searchable Claude Code gaps corpus with severity ratings and workarounds. Quick links: Check your setup · Install hooks · Known limitations ·...

LID

██╗ ██╗██████╗ ██║ ██║██╔══██╗ ██║ ██║██║ ██║ ██║ ██║██║ ██║ ███████╗██║██████╔╝ ╚══════╝╚═╝╚═════╝ Linux Integrity Drift — "Linux está muriendo" — Descubrimiento sistemático de rutas de código del kernel que omiten las garantías de seguridad de LSM La puerta nunca fue derribada. Simplemente la...

allstar

Allstar !IMPORTANT La GitHub App de Allstar alojada por OpenSSF ha sido retirada. Allstar, el subproyecto de OpenSSF Scorecard, continúa manteniéndose: ahora debes ejecutarlo tú mismo, ya sea como una GitHub Action o como un daemon de servicio. Consulta ossf/allstar881 para más detalles. Si tu...

prismor

Prismor Runtime security for Claude Code, Codex, Langchain and other AI agents frameworks/harness. Prismor is highly customizable based on user's own policies. Observe or enforce mode to see agent activity in a local self-serve dashboard...

gatekeeper

Gatekeeper ¿En qué se diferencia Gatekeeper de OPA? En comparación con el uso de OPA con su sidecar kube-mgmt también conocido como Gatekeeper v1.0, Gatekeeper introduce la siguiente funcionalidad: Una biblioteca de políticas extensible y parametrizada CRDs nativos de Kubernetes para instanciar l...

opa

Open Policy Agent Open Policy Agent（OPA）是一个开源、通用策略引擎，可在整个技术栈中实现统一、上下文感知的策略执行。 OPA 很荣幸成为 Cloud Native Computing Foundation（CNCF）领域的毕业项目。详情请阅读 CNCF 公告。 开始使用 OPA 使用 Rego Playground 编写您的第一条 Rego 策略，或通过它分享您的工作以获取反馈和支持。如果您不确定从何入手，可以查看 访问控制示例。 安装 VS Code 扩展 以在本地开始使用实时诊断、调试和格式化功能。有关其他受支持的编辑器，请参阅 Editor a...

Responsible-Alliance-Protocol

Teleological Bounding Protocol TBP v4.2.1 A policy-enforcement and cryptographic audit layer for autonomous AI agents. TBP blocks specific classes of agent action — autonomous financial transfers, industrial-control-system access, weapons-system integration — at the execution layer, outside the...

EUVD-2026-80252

On affected platforms running Arista EOS, if OpenConfig is configured and running a gNMI server on the system, and if gNSI Pathz is configured and a gNSI Pathz policy is present on the system, then gNMI may fail to correctly enforce the rules in this policy if both a group rule and a user rule fo...

aegis-latent-core

Aegis Latent Core AI Governance and Cryptographic Evidence Gateway Aegis sits between your application and your model provider. For every governed call it applies policy, forwards the request, and commits a signed, hash-linked evidence record before the response reaches your caller — together wit...

agent

Bomfather Agent Bomfather Agent is an eBPF-based agent that runs in the kernel space to block actions based on a policy. We built this agent to solve the problems we had with existing solutions. 1. They were too complex to set up and use. 2. They were too slow and inefficient. 3. And even if they...

prismor v1.51.0

Prismor Runtime security for Claude Code, Codex, Langchain and other AI agents frameworks/harness. Prismor is highly customizable based on user's own policies. Observe or enforce mode to see agent activity in a local self-serve dashboard Website • Onboard with Skill !Kimi...

Astra Linux – Vulnerability in Chromium

Insufficient policy enforcement in Extensions in Google Chrome prior to 149.0.7827.53 allowed an attacker who convinced a user to install a malicious extension to bypass site isolation via a crafted Chrome Extension. Chromium security severity: Medium...

Astra Linux – Vulnerability in Chromium

Insufficient policy enforcement in the Sandbox feature of Google Chrome on Linux before version 149.0.7827.53 allowed a remote attacker to potentially perform a sandbox escape through a crafted HTML page. Chromium security severity: Low...

aegisagent

AegisAgent — AI Agent Runtime Security Gateway AI Agent Runtime Security Gateway — cryptographically binds every tool call to the authentic model completion, zero-trust policy enforcement, and integrated sandbox isolation and human approval. Background: Why AegisAgent In August 2026, the Cloud...

conductai

Conduct Governance for AI agents. Ship in 60 seconds. Built for engineering teams. Install in 10 minutes. Evidence for the CISO from day one. 60-second trial no install root@kitploit: curl -fsSL conductai.ai/install | sh Prompts for email + company, provisions a 7-day trial workspace, drops...

EUVD-2026-75258

A vulnerability in the EndPoint Data Loss Prevention DLP enforcement of Palo Alto Networks Prisma® Access Agent enables a local user to bypass configured DLP policy enforcement controls and exfiltrate sensitive data. This Prisma Access Agent on macOS, Linux, iOS, Android and Chrome OS is not...