Grades are a hygiene check, not a security guarantee.

MCP, MCP server

agenticmail

agenticmail, an MCP server listed in the PlugVet directory.

Compatibility: Not stated.

Grade D

Two or more Medium findings, or a High finding. Only try it in a sandbox.

Graded by PlugVetRubric v2

Not a guarantee. A hygiene check of the source at the commit shown, not a security audit.

Rescanned at commit a3e1cf0d0929, unchanged since the check below.

INSTALL_REMOTE_SCRIPT SECRETS_PATH_CREDENTIAL

Why this grade

  • INSTALL_REMOTE_SCRIPT High

    Fetches a script from the network and runs it (a pipe to a shell, or an install hook with a URL).

    AGENTS.md, line 22 curl -fsSL https://raw.githubusercontent.com/agenticmail/agenticmail/main/install.sh | bash

  • SECRETS_PATH_CREDENTIAL Medium

    Mentions a credential store path (~/.ssh, id_rsa, .npmrc, .aws/credentials, credentials.json, .netrc).

    packages/claudecode/src/install.ts, line 19 * - We do NOT touch ~/.claude/.credentials.json (the host Claude OAuth token).

Any High, or two or more Medium findings, give D. One Medium gives C. Low findings or a security Note give B. Each code names a finding behind the letter.

If you think this grade is wrong, email [email protected] with the entry link and your evidence. We aim to acknowledge within two working days and decide within seven. If we confirm an error, we aim to correct it within 24 hours of confirming it. These are aims, not guarantees.

Grades are a hygiene check of the source at the commit shown, on the date checked, not a security audit or a guarantee. The free directory grades are automated. Before release, a PlugVet engineer reviews every paid report and any grade we hold back, including all F grades, against the source code and the evidence we quote.

What was checked

Plain notes from the hygiene checks.

  • Permissions

    Note

    requests shell access. The manifest names this permission.

    PERMISSION_SHELL_DECLARED

    packages/core/src/gateway/relay.ts, line 69

    // Subprocess errors: child_process.exec rejection carries stderr/stdout/exit code.

  • Install and update

    Serious

    install fetches a script from the network. The docs document an installer that pipes a download into a shell. README documents an installer that pipes a download into a shell.

    INSTALL_REMOTE_SCRIPT INSTALL_DOCUMENTED_INSTALLER

    AGENTS.md, line 22

    curl -fsSL https://raw.githubusercontent.com/agenticmail/agenticmail/main/install.sh | bash

    CLAUDE.md, line 15

    curl -fsSL https://raw.githubusercontent.com/agenticmail/agenticmail/main/install.sh | bash

    README.md, line 19

    > curl -fsSL https://raw.githubusercontent.com/agenticmail/agenticmail/main/install.sh | bash

    Show more

    README.md, line 436

    curl -fsSL https://raw.githubusercontent.com/agenticmail/agenticmail/main/install.sh | bash

    install.sh, line 6

    # curl -fsSL https://raw.githubusercontent.com/agenticmail/agenticmail/main/install.sh | bash

    install.sh, line 7

    # curl -fsSL https://raw.githubusercontent.com/agenticmail/agenticmail/main/install.sh | bash -s -- --dry-run

    install.sh, line 109

    printf " ${C_GREEN}curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.40.1/install.sh | bash${C_RESET}\n"

    install.sh, line 116

    dnf|yum) printf " ${C_GREEN}curl -fsSL https://rpm.nodesource.com/setup_22.x | sudo bash -${C_RESET}\n ${C_GREEN}sudo ${PKG_MGR} install -y nodejs${C_RESET}\n\n" ;;

    agenticmail/README.md, line 17

    > curl -fsSL https://raw.githubusercontent.com/agenticmail/agenticmail/main/install.sh | bash

    packages/core/src/setup/installer.ts, line 406

    'wsl', ['-e', 'sh', '-c', 'curl -fsSL https://get.docker.com | sh'],

    packages/core/src/setup/installer.ts, line 448

    'Or install WSL2 and Docker Engine: wsl --install && wsl -e sh -c "curl -fsSL https://get.docker.com | sh"',

    CHANGELOG.md, line 6203

    curl -fsSL https://raw.githubusercontent.com/agenticmail/agenticmail/main/install.sh | bash

    plugin/skills/install/SKILL.md, line 45

    curl -fsSL https://raw.githubusercontent.com/agenticmail/agenticmail/main/install.sh | bash

  • Network

    Concern

    can reach a host that is not written as a fixed address. can reach deb.nodesource.com. The description does not name that host. can reach api.anthropic.com. The description does not name that host. can reach api.ipify.org. The description does not name that host. can reach ifconfig.me. The description does not name that host. can reach get.docker.com. The description does not name that host.

    NETWORK_NO_FIXED_HOST NETWORK_UNNAMED_HOST

    AGENTS.md, line 21

    # Option A (recommended): one-line curl installer

    AGENTS.md, line 621

    curl -s http://127.0.0.1:3829/api/agenticmail/health # raw API health

    install.sh, line 115

    apt) printf " ${C_GREEN}curl -fsSL https://deb.nodesource.com/setup_22.x | sudo -E bash -${C_RESET}\n ${C_GREEN}sudo apt-get install -y nodejs${C_RESET}\n\n" ;;

    Show more

    install.sh, line 133

    linux) printf " ${C_GREEN}curl -fsSL https://deb.nodesource.com/setup_22.x | sudo -E bash - && sudo apt-get install -y nodejs${C_RESET}\n" ;;

    agenticmail/src/anthropic-token.ts, line 126

    response = await fetch('https://api.anthropic.com/v1/messages', {

    agenticmail/src/shell.ts, line 244

    return fetch(`${apiBase}${path}`, {

    agenticmail/src/shell.ts, line 368

    return await fetch(url, {

    agenticmail/src/shell.ts, line 767

    // blocks or curl `Authorization` headers. CodeQL

    agenticmail/src/shell.ts, line 3380

    const resp = await fetch(`${apiBase}/api/agenticmail/sms/config`, {

    packages/core/src/setup/index.ts, line 251

    test: ["CMD-SHELL", "curl -sf http://localhost:8080/health || true"]

    packages/openclaw/index.ts, line 543

    const resp = await fetch(`http://127.0.0.1:${gwPort}/hooks/wake`, {

  • Secrets

    Concern

    reads a credential or environment file.

    SECRETS_ENV_READ SECRETS_PATH_CREDENTIAL SECRETS_PATH_DOTENV

    agenticmail/src/shell.ts, line 2870

    gatewayToken = process.env.OPENCLAW_GATEWAY_TOKEN || gatewayToken;

    agenticmail/telegram-bridge/bridge.mjs, line 134

    if (process.env.TELEGRAM_BOT_TOKEN) return process.env.TELEGRAM_BOT_TOKEN.trim();

    packages/claudecode/src/install.ts, line 19

    * - We do NOT touch ~/.claude/.credentials.json (the host Claude OAuth token).

    Show more

    agenticmail/telegram-bridge/lib/claude-runner.mjs, line 95

    if (process.env.ANTHROPIC_AUTH_TOKEN) {

    agenticmail/telegram-bridge/lib/claude-runner.mjs, line 96

    return { token: process.env.ANTHROPIC_AUTH_TOKEN, source: 'env' };

    packages/api/src/realtime-ws.ts, line 260

    if (!deps.config.voiceRuntime && !deps.config.openaiApiKey && !process.env.OPENAI_API_KEY) {

    packages/api/src/realtime-ws.ts, line 373

    if (!deps.config.voiceRuntime && !deps.config.openaiApiKey && !process.env.OPENAI_API_KEY) {

    packages/api/src/routes/inbound.ts, line 18

    const INBOUND_SECRET = process.env.AGENTICMAIL_INBOUND_SECRET || (() => {

    packages/claudecode/src/cli.ts, line 86

    masterKey: process.env.AGENTICMAIL_MASTER_KEY,

    packages/core/src/mail/outbound-guard.ts, line 307

    description: 'Multiple environment variable assignments detected (possible .env leak)',

    packages/core/src/mail/outbound-guard.ts, line 400

    const HIGH_RISK_EXTENSIONS = new Set(['.pem', '.key', '.p12', '.pfx', '.env', '.credentials', '.keystore', '.jks', '.p8']);

    packages/core/src/mail/outbound-guard.ts, line 442

    '.env', '.conf', '.config', '.ini', '.sql', '.js', '.ts', '.py',

    packages/core/src/setup/index.ts, line 116

    const envPath = join(dataDir, '.env');

    packages/core/src/setup/index.ts, line 126

    // back, and the .env file gets the same value so subsequent

    packages/core/src/setup/index.ts, line 136

    // Append the inbound line to .env so `agenticmail start`

    packages/core/src/setup/index.ts, line 137

    // (which sources .env, not config.json) sees it on the next

  • Agent instructions

    Pass

    No instruction to ignore earlier instructions or to hide a step.

  • Obfuscation

    Note

    a file was over the read cap and was not fully read. the file cap was reached before every file was read.

    OBFUSCATION_FILE_OVER_READ_CAP OBFUSCATION_FILE_CAP_REACHED

    CHANGELOG.md, line 1

    # Changelog

    agenticmail/src/cli.ts, line 1

    #!/usr/bin/env node

    packages/core/src/skills/built-in/invoke-regulator-firmly.json, line 1

    {

  • Licence

    Pass

    A licence file is present (LICENSE).

  • Maintainer activity

    Pass

    The latest commit is within the last 365 days.

Get the full report on this tool, £49

Note

Hygiene check of commit a3e1cf0d0929. requests shell access. The manifest names this permission. install fetches a script from the network. The docs document an installer that pipes a download into a shell. README documents an installer that pipes a download into a shell. can reach a host that is not written as a fixed address. can reach deb.nodesource.com. The description does not name that host. can reach api.anthropic.com. The description does not name that host. can reach api.ipify.org. The description does not name that host. can reach ifconfig.me. The description does not name that host. can reach get.docker.com. The description does not name that host. reads a credential

Date and source

Date checked:

View source

github.com

Commit graded: a3e1cf0d09291ebfc22695ebe73affd9bf6e1871

This link goes to the original host. PlugVet does not host or check what you download from there, and installing it is your own decision and risk.

Read how this letter is chosen