agent-sweep

AgentSweep Find and redact secrets in your AI coding agent's local history. Fully offline. Watch the full clip with sound 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...

distributed-system-testing

Distributed Systems Testing Skills Two skills that help an AI coding agent design meaningful tests, run them, and explain the results for systems that store data or run across multiple processes or machines. Start with a product promise—such as “once saving succeeds, the data is still there after...

sandbox-agent

Agents Agent infrastructure from Rivet. Join us on Discord. Projects Project| Directory| Docs ---|---|--- Rivet Agents : run agents such as Pi as durable Rivet Actors @rivet-dev/pi, @rivet-dev/sandbox-adapter| packages/, docs in docs/| rivet.dev/agents/docs Sandbox Agent : run coding agents in...

gryph

AI coding agents have no security boundaries. Gryph is building one. Everyone runs YOLO mode. Gryph enforces guardrails and keeps the audit trail. Quick Start · Demo · Supported Agents · Use Cases · Security Policy AI coding agents Claude Code, Cursor, Windsurf, Gemini CLI, OpenCode can read any...

bubblewrap

Bubblewrap Many container runtime tools like systemd-nspawn, docker, etc. focus on providing infrastructure for system administrators and orchestration tools e.g. Kubernetes to run containers. These tools are not suitable to give to unprivileged users, because it is trivial to turn such access in...

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...

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...

agentbox

Agentbox - Coding Agent Sandbox There's no perfect way to sandbox agents yet, but containers are a practical start. Agentbox is a Docker-based coding agent sandbox, originally inspired by Batrachian Toad, and now generalized to more tools. It provides an isolated environment that works well with...

trustmebro

Bypass llm guardrails by confusing it with fabricated tool output. Results · Installation · Quick start · Rules · Architecture TrustMeBro intercepts command-line tools invoked by coding agents such as Codex, Claude Code, and pi. Rules decide whether to return fabricated output, modify the real...

yolobox

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

AI-Security-Newsletter

AI Security Newsletter - June 2026 A digest of AI security research, insights, reports, upcoming events, and tools & resources. Follow the AISecHub community and our LinkedIn group for additional updates. Also check out our project, Awesome AI Security. Sponsored by InnovGuard.com - Technology...

vibebox

an ultrafast, open-source sandbox for running coding agents safely. English | 简体中文 VibeBox is a per-project micro-VM sandbox for running coding agents on macOS Apple Virtualization Framework. It’s optimized for a daily-driver workflow: fast warm re-entry, explicit mounts, and reusable sessions. W...

conduit

Conduit The on-prem control plane for AI coding agents. Per-engineer cost attribution · hard budgets · egress governance · context-rot observability · audit-ready exports — all inside your VPC. Conduit sits between your AI coding agents Claude Code, Cursor, Codex, Aider and whatever provider you...

vibe-coding-security

Vibe Coding Security Before you tweet your launch, run these 69 checks. They map to the exact patterns behind the Lovable RLS CVE CVE-2025-48757, 170+ apps, 2025, the Moltbook leak 1.5M API tokens, Feb 2026, and the April 2026 Lovable platform breach source code + service keys of other users'...

compaction-laundering

Compaction Laundering When a coding agent summarizes its own conversation, a line an attacker planted in a file it read can come out recorded as the user's own instruction — and get executed. Security research into context compaction conversation summarization in open-source coding agents. The...

guardskill

GuardSkill A repository can make your coding agent run code the moment it opens the folder. GuardSkill checks for that before you do. npx guardskill . Read-only. No network calls, no telemetry, no configuration, no account, no dependencies. It reads git configuration and hook scripts, prints what...

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...

ranwhat

ranwhat ranwhat checks whether any of your secrets have leaked into your coding agents' history, and where. It also checks whether your agent ran anything sketchy: read your SSH key, force-pushed, piped a script from the internet into a shell, published a package. It reads the history that Claude...

super-trouper

Super Trouper An MCP server for the Frida reverse engineering toolkit. Super Trouper runs an MCP server over STDIO that exposes Frida capabilities as tools for coding agents. It can connect to local, USB, and remote devices; inspect applications and processes; manage process sessions; and load,...

When Coding Agents Get Arms: Safety Risks across the Digital-Physical Boundary

Advances in spatial understanding have enabled frontier models to power coding agents that control a real robot arm zero-shot and end-to-end, without task-specific demonstrations or retraining. This brings two new safety challenges. First, the extensive knowledge of frontier models lets these...