conduit

Conduit El plano de control on-premise para agentes de codificación de IA. Atribución de costos por ingeniero · presupuestos estrictos · gobierno de egreso · observabilidad de rotación de contexto · exportaciones listas para auditoría — todo dentro de tu VPC. Conduit se sitúa entre tus agentes de...

AI-Security-Newsletter

Boletín de Seguridad de IA - Junio 2026 Un resumen de investigaciones, ideas, informes, próximos eventos y herramientas y recursos de seguridad de IA. Sigue a la comunidad AISecHub y a nuestro grupo de LinkedIn para obtener actualizaciones adicionales. También echa un vistazo a nuestro proyecto,...

distributed-system-testing

Habilidades para pruebas de sistemas distribuidos Dos habilidades para agentes de codificación de IA que diseñan y ejecutan pruebas impulsadas por afirmaciones para sistemas distribuidos y con estado. Juntas producen un plan de pruebas Markdown estructurado y un informe de hallazgos con veredicto...

yolobox

██╗ ██╗ ██████╗ ██╗ ██████╗ ██████╗ ██████╗ ██╗ ██╗ ╚██╗ ██╔╝██╔═══██╗██║ ██╔═══██╗██╔══██╗██╔═══██╗╚██╗██╔╝ ╚████╔╝ ██║ ██║██║ ██║ ██║██████╔╝██║ ██║ ╚███╔╝ ╚██╔╝ ██║ ██║██║ ██║ ██║██╔══██╗██║ ██║ ██╔██╗ ██║ ╚██████╔╝███████╗╚██████╔╝██████╔╝╚██████╔╝██╔╝ ██╗ ╚═╝ ╚═════╝ ╚══════╝ ╚═════╝ ╚═════╝...

lowkey

Self-Hosted AI Coding Agents on AWS — OpenClaw, Claude Code, Codex, Kiro, NemoClaw, Hermes ▶️ Watch the full walkthrough on YouTube 📝 Read the blog post: "I Gave My Agent Its Own AWS Account" TL;DR — deploy Lowkey: curl -sfL install.lowkey.run | bash Works in bash , zsh , and AWS CloudShell. The...

lowkey

Agentes de Codificación de IA Auto-Alojados en AWS — OpenClaw, Claude Code, Codex, Kiro, NemoClaw, Hermes ▶️ Mira el tutorial completo en YouTube 📝 Lee el artículo del blog: "Le di a mi agente su propia cuenta de AWS" TL;DR — despliega Lowkey: curl -sfL install.lowkey.run | bash Funciona en bash ,...

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 Website • Onboard with Skill...

agent-sweep

AgentSweep Encuentra y redacta secretos en el historial local de tu agente de codificación con IA. Totalmente offline. Ver el clip completo con sonido Prevención: No pegues claves de API en agentes de IA respaldados en la nube en absoluto. La clave transita por los servidores del proveedor antes ...

vibe-coding-security

Vibe Coding Security Antes de que tuitees tu lanzamiento, ejecuta estas 69 comprobaciones. Se corresponden con los patrones exactos detrás del CVE de RLS de Lovable CVE-2025-48757, 170+ apps, 2025, la filtración de Moltbook 1,5 millones de tokens de API, febrero de 2026 y la brecha de la platafor...

ai-agent-security-research

AI Agent Security Research Open security research on AI coding agent infrastructure. Published by Hodge Luke Digital Intelligence Agency What This Is This repository contains security research, vulnerability analysis, and remediation guidance for AI coding agent platforms. Every advisory includes...

CVE-2026-57586 CodeRAG: Gradle Wrapper Execution During Dependency Discovery Enables Arbitrary Code Execution

CodeRAG is a lightweight semantic code search and distillation utility for AI coding agents. Prior to 1.3.1, the default agent-coderag sync flow in coderag/entry/cli.py calls syncdependencies for an indexed path, and coderag/core/manager.py treats build.gradle or build.gradle.kts as sufficient to...

sage v0.13.0

Sage Safety for Agents — Agent Detection & Response for AI coding assistants Sage is a lightweight security layer that protects AI agents from executing dangerous actions. It intercepts tool calls — shell commands, URL fetches, file writes — and checks them against multiple threat detection layer...

prismor v1.44.0

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...

Malicious .git Configs Can Make Claude, Codex, Cursor, and Other AI Agents Run Attacker Code

Manifold Security has disclosed eight security flaws across seven command-line AI coding agents in which a repository's own Git configuration names a command that the agent runs on the developer's machine, four of them still unpatched at publication. The command executes as the user, outside the...

bromure agentic-coding-v4.6.0

Bromure Secure, ephemeral computing in disposable Linux VMs on macOS. → Full details, screenshots, and downloads at bromure.io This repo ships two sibling apps, both built on Apple's Virtualization.framework: Bromure — every browser session runs in a throwaway Linux VM. Close the window, the VM i...

PT-2026-84855

Name of the Vulnerable Software and Affected Versions Hermes version 0.21.0 Description An issue exists where coding agents execute git status or git diff for context gathering before trust prompts are presented to the user. If a repository is delivered as files such as via zip, sync, or USB rath...

yolobox v0.19.4

██╗ ██╗ ██████╗ ██╗ ██████╗ ██████╗ ██████╗ ██╗ ██╗ ╚██╗ ██╔╝██╔═══██╗██║ ██╔═══██╗██╔══██╗██╔═══██╗╚██╗██╔╝ ╚████╔╝ ██║ ██║██║ ██║ ██║██████╔╝██║ ██║ ╚███╔╝ ╚██╔╝ ██║ ██║██║ ██║ ██║██╔══██╗██║ ██║ ██╔██╗ ██║ ╚██████╔╝███████╗╚██████╔╝██████╔╝╚██████╔╝██╔╝ ██╗ ╚═╝ ╚═════╝ ╚══════╝ ╚═════╝ ╚═════╝...