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: root@kitploit: curl -sfL install.lowkey.run | bash Works in bash , zsh , and AWS...

lowkey

在 AWS 上自托管 AI 编码代理 — OpenClaw, Claude Code, Codex, Kiro, NemoClaw, Hermes ▶️ 在 YouTube 上观看完整演示 📝 阅读博客文章：我给代理开了个 AWS 账号，它就能编码、部署和调试全栈应用了 简而言之 — 部署 Lowkey： root@kitploit: curl -sfL install.lowkey.run | bash 适用于 bash 、zsh 和 AWS CloudShell 。安装程序会交互式地引导你选择 pack、profile 和部署方法。 一行命令示例（非交互式）：...

distributed-system-testing

Distributed Systems Testing Skills Two skills for AI coding agents that design and run claim-driven tests for distributed and stateful systems. Together they produce a structured Markdown test plan and a findings report with 10-state verdicts and an explicit SUT / harness / checker / environment...

prismor

Prismor 为 Claude Code、Codex、Langchain 及其他 AI 智能体框架/运行环境提供运行时安全防护。 Prismor 可基于用户自定义策略进行高度定制。通过观察或强制执行模式，在本地自助仪表盘中查看智能体活动 网站 • 通过 Skill 快速上手 !Google Antigravityhttps://d2...

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,...

agent-sweep

AgentSweep Find and redact secrets in your AI coding agent's local history. Fully offline. Prevention: Don't paste API keys into cloud-backed AI agents at all — the key transits the provider's servers before it ever hits your disk. If you already did: agentsweep removes the remaining local attack...

conduit

Conduit 面向AI编码代理的本地控制平面。 按工程师计费 · 硬预算 · 出站治理 · 上下文膨胀可观测性 · 审计就绪导出 —— 全部位于您的VPC内。 Conduit 位于您的 AI 编码代理（Claude Code、Cursor、Codex、Aider）与您已使用的任何提供商（Anthropic、OpenAI、Bedrock、Azure —— 或您现有的 LiteLLM / Portkey 部署）之间。只需一个环境变量即可接入，客户端无需更改，提示和补全内容永不存储。 root@kitploit: Claude Code / Cursor / Codex │...

yolobox

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

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

Investigación de Seguridad de Agentes de IA Investigación de seguridad de código abierto sobre la infraestructura de agentes de codificación de IA. Publicado por Hodge Luke Digital Intelligence Agency Qué es esto Este repositorio contiene investigación de seguridad, análisis de vulnerabilidades y...

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...

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 !Kimi...

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...

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

root@kitploit: ██╗ ██╗ ██████╗ ██╗ ██████╗ ██████╗ ██████╗ ██╗ ██╗ ╚██╗ ██╔╝██╔═══██╗██║ ██╔═══██╗██╔══██╗██╔═══██╗╚██╗██╔╝ ╚████╔╝ ██║ ██║██║ ██║ ██║██████╔╝██║ ██║ ╚███╔╝ ╚██╔╝ ██║ ██║██║ ██║ ██║██╔══██╗██║ ██║ ██╔██╗ ██║ ╚██████╔╝███████╗╚██████╔╝██████╔╝╚██████╔╝██╔╝ ██╗ ╚═╝ ╚═════╝ ╚══════╝...