ATR (Agent Threat Rules) (Agent-Threat-Rule/agent-threat-rules) — Sandbox, Security & Governance

Install

npm install -g agent-threat-rules

Repository reader

Read the project’s README, skills and supporting Markdown here. Rendered view is shown first; source is one click away when you need the exact text.

Fetched from GitHub

Loading the project’s README…

Public files are loaded on demand from the repository. The atlas does not copy or modify them.

Derived from the project's own README, install route, CI configuration and release assets — not from running it.
Platform	Runs here	On what evidence
Windows	Likely	Inferred from the language or runtime. Nothing in the project says so.
WSL2	Likely	Inferred from the language or runtime. Nothing in the project says so.
macOS	Likely	Inferred from the language or runtime. Nothing in the project says so.
Linux	Likely	Inferred from the language or runtime. Nothing in the project says so.
Docker	Yes	Stated in the project's own README, install route, CI config or release assets.

Named by 1 of the 39 lists the atlas merges.

One topic, 1 harness. Each link is a prerendered page of everything else in that slice.

Closest first — projects that plug into the same harnesses, then the ones the most lists agreed on.

Brood Boxstacklok/brood-boxRun AI coding agents (Claude Code, Codex, OpenCode) inside hardware-isolated microVMs with snapshot isolation, egress control, and MCP authorization
Cordumcordum-io/cordumCordum (cordum.io) is a platform-only control plane for autonomous AI Agents and external workers. It uses NATS for the bus, Redis for state and…
Node9node9-ai/node9-proxySecurity and governance layer that checks every tool call from coding agents and MCP servers before it runs: credential jail, secret and PII…
OneCLIonecli/onecliOpen-source credential vault for AI agents. A Rust HTTP gateway intercepts agent requests and injects API credentials transparently, so agents never…
Open AgentTh0rgal/orbSelf-hosted control plane for Claude Code with isolated container workspaces and real-time mission streaming
AegisJustin0504/AegisPre-execution firewall that intercepts, classifies, and blocks agent tool calls before they execute, with a compliance cockpit for real-time…
Agent Scansnyk/agent-scanSnyk's scanner for local agent supply chains, covering MCP servers and skills with checks for prompt injection, tool poisoning, toxic flows, and…
agent-airlocksattyamjjain/agent-airlockDeny-by-default contract layer for agent tool calls that adds Pydantic strict validation, ghost-argument stripping and retryable fix hints through…