zn

---

For: developers using Claude Code, Codex CLI, Cursor, OpenCode or any MCP client, and teams building agents with MCP, LangChain, CrewAI or LlamaIndex.

What it does: keeps secret values out of what your agent sends to its model, checks what your agent reads and calls for prompt injection, and audits prompts, skills and configs. Everything runs on your machine, is MIT-licensed and needs no account. The Python package has no runtime dependencies; the npm package's only one is age-encryption (with its @noble/@scure dependencies) for the secret vault, bundled in the package.

Install

Everything runs on your machine; no account or API key is needed. You need Node.js 18 or later (the LTS version from nodejs.org). With an older Node.js, the zn-gate and zn commands stop and say how to install it.

One command for the coding agents on your machine:

npx -y zn-gate init

It finds Claude Code, Codex CLI, Cursor and OpenCode, shows the setup for each one that is not protected yet (the zn-gate plugin for Claude Code, zn's hooks for the others), runs each step after you confirm it, and ends with zn-gate check. Run it yourself in your own terminal, with no arguments: when an AI agent or a script runs it, it only prints the steps.

Windows PowerShell: npm and npx can fail with "running scripts is disabled on this system", because the default execution policy blocks npm.ps1. Use npm.cmd, npx.cmd and zn.cmd instead (for example npm.cmd install -g zn-gate), run the commands from Command Prompt, or allow local scripts for your account with Set-ExecutionPolicy -Scope CurrentUser RemoteSigned.

Then keep your .env values in the vault. With the plugin or the hooks, the agent cannot read .env files with real values; move them into zn-gate's encrypted vault, and the file keeps markers such as __ZN_STRIPE_KEY__:

npx -y zn-gate unlock            # creates the vault the first time
npx -y zn-gate env shadow .env

After this, your own app also reads the markers in .env: start it with zn-gate's run command once you allow it (docs/secrets.md). env shadow tells you how to undo it.

Five-minute walkthrough: docs/secrets.md. Limits: docs/threat-model.md.

One agent at a time (the same steps init runs):

Claude Code: the plugin. You also need Git and Claude Code 2.1.295 or later.

claude plugin marketplace add usezn/zn
claude plugin install zn-gate@usezn

Already ran zn hooks install claude-code before? Run zn hooks uninstall claude-code first, otherwise both sets of hooks run.

Start a new Claude Code session. Claude Code is then blocked from reading .env files with real values and credential files, secrets in what its tools return are replaced with markers or redacted before the model sees them, a secret pasted into a prompt is blocked, and Claude can check untrusted text for prompt injection. Not covered: Claude Code sessions in the cloud, Cowork and chat. Details: plugins/zn-gate.

Codex CLI, Cursor or OpenCode: the hooks.

npm install -g zn-gate
zn hooks install codex           # or: cursor, opencode

In Codex, approve the new hooks with /hooks. In Cursor, shell output and file contents are not scrubbed. What each agent supports: docs/compat.md.

Other editors (VS Code, Antigravity, Windsurf, Cline, Zed, JetBrains, Continue): zn-gate works there as an MCP server only. Setup for each one: usezn.com/docs/integrations/editors.

Python: for agents you build yourself (rules engine and secret redaction for LangChain, CrewAI, LlamaIndex or plain tool calling). It does not protect Claude Code, Codex, Cursor or other coding agents. Install it in a virtual environment; many recent Linux systems, and Homebrew's Python on macOS, refuse pip install outside one ("externally-managed-environment"):

python3 -m venv .venv
.venv/bin/pip install zn-gate      # Windows: .venv\Scripts\pip install zn-gate

On Debian and Ubuntu, python3 -m venv needs the python3-venv package first: sudo apt install python3-venv.

zn-gate as an MCP server only (the agent calls it when it decides to; not automatic protection):

claude mcp add zn-gate -- npx -y zn-gate mcp     # Claude Code
codex mcp add zn-gate -- npx -y zn-gate mcp      # Codex CLI

Cursor (~/.cursor/mcp.json) and other editors: { "mcpServers": { "zn-gate": { "command": "npx", "args": ["-y", "zn-gate", "mcp"] } } }. OpenCode (~/.config/opencode/opencode.json): { "mcp": { "zn-gate": { "type": "local", "command": ["npx", "-y", "zn-gate", "mcp"], "enabled": true } } }.

Protect the MCP servers you already use. init finds them in your agent configs, writes a backup, and wraps each local server with the zn-gate proxy:

npx -y zn-gate init --dry-run   # preview
npx -y zn-gate init --wrap-mcp  # wrap (backup first)
npx -y zn-gate init --revert    # undo

It reads Claude Desktop, Claude Code (~/.claude.json), Cursor (~/.cursor/mcp.json), Codex CLI (~/.codex/config.toml), OpenCode (~/.config/opencode/opencode.json) and Antigravity (~/.gemini/antigravity/mcp_config.json). Full list and rules.

Check that it works

npx -y zn-gate check

For each agent set up for your user, zn-gate asks its hook to let the agent read a .env file with a fake key and an ordinary file, in a temporary folder. It shows what your agent would be told, and a line that says NOT protected says how to fix it. Nothing is sent over the network and no setting changes. What the output means.

npx -y zn-gate test

This runs the local self-test (51 curated vectors: 26 attacks, 25 benign) and shows per-decision latency on your machine. It is a smoke test, not a detection rate. Nothing is sent over the network.

For developers: see the redaction by hand. Send a tool output with a fake AWS key (AWS's documentation example) and a database password through zn-gate, exactly as your agent would, and look for sanitized_content in the output; that field is what the model would see:

printf '%s\n' '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"check_tool_result","arguments":{"tool_name":"read_file","content":"AWS_ACCESS_KEY_ID=AKIAIOSFODNN7EXAMPLE\nDATABASE_URL=postgres://app:hunter2@db:5432/main"}}}' \
  | npx -y zn-gate@latest mcp

Python equivalent:

.venv/bin/python -c "from zn_gate import sanitize_tool_result as s; print(s('read_file', 'AWS_ACCESS_KEY_ID=AKIAIOSFODNN7EXAMPLE')['sanitized_content'])"

What each piece does

Where zn-gate sits in a tool call, as an MCP server or as the shield proxy around other servers:

Scrubber: secrets stay out of the model's context

• Today, through zn-gate: redacts AWS keys, OpenAI and Anthropic keys, GitHub tokens, JWTs, private keys and database URL passwords in everything that passes through zn-gate: tool output checked with check_tool_result, tool arguments checked with check_tool_call, and output of MCP servers wrapped by zn-gate shield / init. Python: sanitize_tool_result, @guard(mask_secrets=True) and the framework integrations.
• Today, agent hooks and vault (npm package): hooks for Claude Code, Codex CLI and OpenCode scrub the output of the agents' built-in tools and block pasted secrets (in Cursor only MCP tool output is scrubbed); a local encrypted vault with stable markers (__ZN_AWS_KEY_1__); zn run fills values only into commands you approved; personal data (cards, IBAN, national IDs, e-mail, phone) is detected too. What each agent allows differs: see docs/compat.md.

Galvanize: prompt-injection detection

• Today, local: a deterministic rules engine (signatures plus normalization against homoglyphs, zero-width characters, BiDi overrides, comment splicing and Base64) checks prompts, tool arguments, tool output and MCP tool descriptions.
• Today, optional cloud check: the Galvanize 2 classifier (open weights on Hugging Face, Apache-2.0) can also check prompts sent to analyze_prompt, only if you set ZN_CLOUD=1 and ZN_API_KEY. The secrets zn-gate detects are removed from the prompt on your machine before it is sent; personal data is not removed on this path.
• Roadmap: running Galvanize locally inside zn-gate.

Scan: audit what your agent is about to trust

• Today: zn-gate scan <path> audits prompt templates, AGENTS.md / SKILL.md files and configs for injection traps and leaked secrets (exit code 1 on findings, for CI). A leaked secret is reported as Secret found, with the next step: npx -y zn-gate env shadow <file> moves the values of a .env file into the local vault, npx -y zn-gate secret set NAME stores any other one. It finds provider keys and tokens, opaque Authorization: Bearer tokens, passwords in URLs, and secrets passed as command-line flags (--token=...) or assigned to a name such as password or api_key. The same check runs as a GitHub Action. MCP servers can be checked on the web at usezn.com/scan.
• Roadmap: auditing MCP servers and skills from the CLI before you add them.

What the cloud adds for teams

Everything above runs locally, for free, with no account. The optional cloud at usezn.com is for teams that need a shared record of what their agents did:

• Audit and traceability: an evidence dashboard with the metadata of each cloud decision (verdict, rule, score, latency), 90-day retention and CSV/JSONL export.
• A larger detection model for prompts, when you opt in (ZN_CLOUD=1).
• Team controls (shared policies, organization-level audit): in progress.

By default nothing is sent. If you set ZN_CLOUD=1 and an API key (or the API key option of the Claude Code plugin), analyze sends the prompt text after removing the secrets zn-gate detects locally: personal data is not removed on this path, and a secret it does not detect would be sent with the text. The dashboard keeps the metadata of each cloud decision. Tool output and tool-call arguments are never sent.

What leaves your machine

Nothing, by default.

Data	Evaluated	Sent anywhere?
Tool output (check_tool_result, shield)	Locally	Never, in any configuration
Tool-call arguments (check_tool_call, shield)	Locally	Never, in any configuration
MCP tool and parameter descriptions (shield)	Locally	Never, in any configuration
Counts of what zn-gate did (zn-gate stats: checks, blocks, secrets replaced, per secret type)	Written locally to ~/.zn/stats.json	Never, unless you turn on zn-gate stats share on: then one report a day with a random installation id, the day, the zn-gate, OS and Node.js versions, the agent and part of zn-gate used most, and the number of secrets found per built-in type (never values, prompts, variable or secret names, paths, hosts or emails). zn-gate stats share show shows it first.
Prompts (analyze_prompt, zn-gate analyze, Python analyze())	Locally	Only if you set both ZN_CLOUD=1 and ZN_API_KEY, or the API key option of the Claude Code plugin (for analyze_prompt only). Detected secrets are removed locally before sending; personal data is not.

ZN_API_KEY alone enables nothing. ZN_LOCAL_ONLY=true overrides ZN_CLOUD=1. npx -y zn-gate status prints what your configuration sends.

1.4.0 and earlier: with ZN_API_KEY set, the Node package sent tool output and tool-call arguments to api.usezn.com without redaction. 1.4.1 removes that path. Details in the CHANGELOG.

Performance and accuracy

We only publish numbers we can reproduce, with the method next to them.

• Latency of the local engine: one table by input size, with hardware, date and the script to reproduce it (bench/bench_by_size.js), in the npm package README. Short summary from that run, with secret redaction (p50): about 0.045 ms for a 200 B prompt, 0.3 ms for a 4 KB tool output, about 4 ms for 64 KB.
• Self-test: 51 curated vectors pass. That is a smoke test, not a detection or false-positive rate.
• Known limitation: on whole source files, the rules can flag ordinary code comments. Version 1.5.0 reduces these on code and documentation, at the cost of letting some loosely worded override attempts through the local rules. To check it on your own source files, run zn-gate scan --code <path>; for the MCP servers you wrap, --shadow logs detections without blocking.
• Known limitation: detection of credentials under prefixed variable names (e.g. OPENAI_API_KEY=) is partial in this release.
• Detection rates: on a private held-out set of 3,309 examples, Galvanize 2 has 83.4% recall at a 0.81% false positive rate (serving threshold 0.662); these numbers are for the cloud classifier, not the local rules engine. Method, per-language results, known weak spots and a reproducible benchmark are in the model card and the announcement. It is one layer of defense, not a guarantee.

Configuration

Variable	Default	Effect
ZN_CLOUD	off	1 lets prompt analysis also query the cloud classifier. Requires ZN_API_KEY.
ZN_API_KEY	unset	API key from usezn.com/dashboard. No effect without ZN_CLOUD=1.
ZN_LOCAL_ONLY	unset	true forces local-only, even with ZN_CLOUD=1.
ZN_STAGE / ZN_API_URL	v30	Cloud endpoint selection.

zn Team: zn team join <token> connects a machine to your organization's signed secrets policy and uploads its audit log (metadata only). What the organization can and cannot change on the machine, offline behavior and the OpenTelemetry export (zn vault log export --otlp): docs/team.md.

Custom rules: add banned patterns and forbidden paths in .znrules or zn.config.json at your project root (example).

Audit log: zn-gate shield appends each decision to ~/.zn/evidence.jsonl as a hash-chained (SHA-256) record with a redacted preview. It detects accidental or partial edits; it is not tamper-proof against someone with write access to the file. Check it with npx -y zn-gate evidence --verify.

GitHub Action

The action installs the published zn-gate packages at an exact version and runs on the runner only; it sends nothing anywhere. It has two checks, chosen with mode:

• scan (default): zn-gate scan looks for prompt-injection traps and leaked secrets in prompts, tool definitions and config files (Python package from PyPI). This is what earlier releases of the action did.
• audit: zn audit reviews what your coding agents are configured to trust: .claude/, .mcp.json, .codex/, .cursor/, hooks, AGENTS.md / CLAUDE.md, plugins and skills (npm package; needs version 1.6.0 or later).
• both: runs the two. With a version older than 1.6.0, or a PyPI-only .post version, it runs the scan only and prints a warning.

Scan prompts on pull requests:

name: AI agent security scan

on:
  pull_request:
    paths:
      - 'prompts/**'
      - '**/*.prompt'
      - '**/AGENTS.md'
      - '**/SKILL.md'

permissions:
  contents: read

jobs:
  zn-gate-scan:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
        with:
          persist-credentials: false
      - name: Scan AI agent prompts and tools
        # Pin the action to a full commit SHA; the comment names the release.
        uses: usezn/zn@98fc10e88c9c364b96fa65acc72a41386f0bd2e4 # v1.10.0
        with:
          version: '1.10.0'
          package-sha256: '36b3fbee7a846a4d8ba7b4c5e8b654d57b9a3fdbb9d99a2839f8cd83433b2d1d'
          path: '.'
          fail-on-threat: 'true'
          format: 'github'

Audit agent configs and plugins on every pull request, and show the findings in code scanning. The audit takes seconds, so the example has no paths: filter: a filter would skip the configs of agents it does not list.

name: AI agent config audit

on:
  pull_request:

permissions:
  contents: read

jobs:
  zn-gate-audit:
    runs-on: ubuntu-latest
    permissions:
      contents: read
      security-events: write   # only for the SARIF upload
      actions: read            # private repositories only, for upload-sarif
    steps:
      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
        with:
          persist-credentials: false
      - name: Audit agent configs
        id: zn
        # Pin to the full commit SHA of the first Action release that has the
        # mode input. The zn-gate package version is set by version below.
        uses: usezn/zn@<commit-sha> # <first Action release with mode>
        with:
          version: '1.10.0'
          mode: 'both'
          format: 'sarif'
          severity-threshold: 'medium'   # stricter than the default (high)
      - name: Upload SARIF
        if: ${{ !cancelled() && steps.zn.outputs.sarif-file != '' }}
        uses: github/codeql-action/upload-sarif@24c54180a607b1449ed407dd24f251e4e9147c8d # v4.38.3
        with:
          sarif_file: ${{ steps.zn.outputs.sarif-file }}

Input	Default	Description
version	1.10.0	Exact zn-gate version to install. Ranges and latest are refused. audit needs 1.6.0 or later.
mode	scan	Requires a release of the action that includes audit mode (see the CHANGELOG). scan, audit or both.
path	.	File or directory to scan. audit needs a directory: with both a file skips the audit with a warning; with audit the step fails.
fail-on-threat	true	Fail the step on findings. For scan, anything found (an injection trap or a secret); for audit, findings at or above severity-threshold. Set false to report only. Any value other than true or false fails the step. true or false, in any case; other values fail the step.
severity-threshold	high	Requires a release of the action that includes audit mode (see the CHANGELOG). Audit only: lowest severity that fails the step when fail-on-threat is true: critical, high (high and critical), medium or low. The scan has no severities, so any scan finding fails.
fail-on	empty	Requires a release of the action that includes audit mode (see the CHANGELOG). Audit only: lowest severity that fails the step (low, medium, high, critical, none), passed as is to zn audit --fail-on. When set, it overrides fail-on-threat and severity-threshold for the audit.
agents	empty	Requires a release of the action that includes audit mode (see the CHANGELOG). Audit only: comma-separated agents to audit (zn audit --agents). Empty audits all supported agents.
format	github	github (inline annotations), text, json or sarif (sarif requires a release of the action that includes audit mode).
sarif-file	empty	Requires a release of the action that includes audit mode (see the CHANGELOG). With format: sarif, where to write the file: inside the workspace or the runner temp directory, and not a symbolic link or under one. Empty writes zn-gate.sarif in a new directory under the runner temp directory.
package-sha256	empty	Requires v1.5.0 or later of the action. SHA-256 of the PyPI wheel for version, as listed on PyPI. When set, the install fails if the downloaded file has a different hash. Older releases of the action ignore this input with only a warning, so no hash is checked.
npm-integrity	empty	Requires a release of the action that includes audit mode (see the CHANGELOG). Integrity string (sha512-...) of the npm tarball for version. When set, the audit fails if the tarball has a different hash.

Output	Description
sarif-file	Requires a release of the action that includes audit mode (see the CHANGELOG). Path of the SARIF file (format: sarif only). Empty if no check produced a report (for example, the scan ended in an error) or the file could not be written.
scan-exit-code	Exit code of the scan: 0 clean (or fail-on-threat: 'false'), 1 something found (an injection trap or a secret), 2 error. Empty if the scan did not run.
audit-exit-code	Requires a release of the action that includes audit mode (see the CHANGELOG). Exit code of the audit: 0 clean, 1 findings at or above fail-on, 2 error. Empty if it did not run.

The scan finds more secret types with each release (1.9.1 added secrets passed as command-line flags and assigned to names such as password or api_key), so a job that fails on findings can start failing on files that passed before: pin version and read the findings before you update it.

Older releases of the action ignore the inputs they do not have, with only a warning: with one of them, mode: audit runs the scan instead.

Which audit findings fail the step: fail-on if it is set; otherwise none when fail-on-threat is false; otherwise severity-threshold. For the scan, only fail-on-threat applies.

With mode: both and format: sarif, the file holds one SARIF run per check (zn-gate scan and the audit's own run), each with its own category, so code scanning tracks their alerts separately. The step fails with the worse of the two results: an error beats findings.

Permissions: the action itself needs only contents: read; add security-events: write to the job only when you upload SARIF (and, in private repositories, actions: read, which upload-sarif needs). Packages are installed without running install scripts or build steps (--only-binary=:all: --no-deps for the wheel, --ignore-scripts for the npm tarball, whose dependencies are bundled) into private directories under the runner temp directory. pip still reads the runner's own pip settings (PIP_* environment variables and pip.conf), so a mirror or proxy you configure there is used; set package-sha256 so that the wheel is checked whatever index it comes from (and npm-integrity for the npm tarball). Run it on pull_request, never on pull_request_target: do not check out untrusted pull-request code in a pull_request_target workflow. With mode: audit or both the action also sets up Node.js 22 for the rest of the job.

Repository layout

• packages/zn-gate: Node.js CLI, MCP server and shield proxy (npm).
• packages/zn-gate-py: Python SDK and CLI (PyPI).
• src/: legacy Rust gateway, not released (docs/rust-core.md).
• bench/: benchmark scripts and results.
• assets/brand/: logo files (SVG master and light/dark variants, PNG lockup and banners).

FAQ

Do I need an account or API key? No. Everything local works without one. An account is only needed for the optional cloud (team audit and the larger detection model).

Does zn-gate slow my agent down? The local check adds under a millisecond for typical prompts and tool outputs (p99 0.8 ms at 4 KB on our test host). See the measured table above.

Will it block legitimate content? Sometimes. Use init --shadow or shield --shadow to log detections without blocking while you evaluate it.

Which agents are supported? Any MCP client. init can rewrite configs for the agents listed under Install.

How do I remove it? npx -y zn-gate init --revert restores your configs from the backup. For a standalone server, remove the zn-gate entry from your agent config.

Security

Report vulnerabilities to security@usezn.com. Policy, scope and safe harbor: SECURITY.md. Hall of Fame: usezn.com/security.

Releases published by the release workflow, starting with the first one after 1.5.0-beta.1, are signed and carry build provenance. 1.5.0-beta.1 and earlier versions were published by hand and have no signatures or provenance. To check a download: docs/verify-release.md.

Contributing

Issues and pull requests are welcome. See CONTRIBUTING.md.

License

MIT. Copyright (c) 2026 usezn (usezn.com). The Galvanize 2 and Galvanize-60M weights are Apache-2.0. The zn-prompt-injection-bench dataset is CC-BY-4.0. The npm package bundles third-party code listed in THIRD_PARTY_NOTICES.md.