Grades are a hygiene check, not a security guarantee.

MCP, MCP server

MCPGateway

Universal MCP aggregation server that routes 300+ tools from multiple MCP servers through a single endpoint with 15 layers of token optimization (95-98% reduction).

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 549f494a9e36, unchanged since the check below.

INSTALL_REMOTE_SCRIPT NETWORK_HOST_FROM_INPUT

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/skills/infra-deploy/SKILL.md, line 138 curl -fsSL https://get.docker.com | sh

  • NETWORK_HOST_FROM_INPUT Medium

    A file takes a URL or endpoint as input and has no fixed host list.

    .agents/skills/hostinger-deploy/SKILL.md, line 34 5. Verify via curl at server level

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

    .agents/skills/daily-standup/scripts/standup_generator.py, line 33

    result = subprocess.run(cmd, capture_output=True, text=True, check=True)

    .agents/skills/daily-standup/scripts/standup_generator.py, line 178

    result = subprocess.run(cmd, capture_output=True, text=True, check=True)

    .agents/skills/git-workflow/scripts/commit_analyzer.py, line 18

    result = subprocess.run(

    Show more

    .agents/skills/git-workflow/scripts/commit_analyzer.py, line 27

    result = subprocess.run(

    .agents/skills/pr-summary/scripts/pr_summary_generator.py, line 16

    result = subprocess.run(

    .agents/skills/pr-summary/scripts/pr_summary_generator.py, line 23

    result = subprocess.run(

    .agents/skills/pr-summary/scripts/pr_summary_generator.py, line 53

    result = subprocess.run(

  • Install and update

    Serious

    install fetches a script from the network.

    INSTALL_REMOTE_SCRIPT

    .agents/skills/infra-deploy/SKILL.md, line 138

    curl -fsSL https://get.docker.com | sh

    .agents/skills/infra-deploy/SKILL.md, line 145

    curl -fsSL https://cdn.coollabs.io/coolify/install.sh | bash

  • Network

    Serious

    accepts a host from input, with no fixed list in this file.

    NETWORK_HOST_FROM_INPUT

    .agents/skills/hostinger-deploy/SKILL.md, line 34

    5. Verify via curl at server level

    .agents/skills/hostinger-deploy/SKILL.md, line 44

    5. Verify via curl at server level

    .agents/skills/hostinger-deploy/SKILL.md, line 54

    5. Verify via curl at server level

    Show more

    .agents/skills/hostinger-deploy/SKILL.md, line 97

    curl -s -o /dev/null -w "%{http_code}" https://yourdomain.com

    .agents/skills/hostinger-deploy/SKILL.md, line 98

    curl -s https://yourdomain.com | head -50

    .agents/skills/hostinger-deploy/SKILL.md, line 101

    curl -s https://yourdomain.com/path/to/changed-file

    .agents/skills/infra-deploy/SKILL.md, line 221

    curl -f http://localhost:3001/health

    .agents/skills/seo-recovery/SKILL.md, line 130

    curl -s "https://example.com/page" | grep -i 'rel="canonical"'

    .agents/skills/seo-recovery/SKILL.md, line 131

    curl -s "https://example.com/page" | grep -i "rel='canonical'"

    src/backend/sse.ts, line 78

    const response = await fetch(sseUrl, {

    src/backend/sse.ts, line 308

    const response = await fetch(this.postUrl!, {

    src/backend/sse.ts, line 360

    await fetch(this.postUrl, {

    src/dashboard/index.ts, line 739

    const response = await fetch(`http://localhost:${process.env.PORT || 3010}/api/code/skills`);

  • Secrets

    Concern

    reads a credential or environment file.

    SECRETS_ENV_READ SECRETS_PATH_DOTENV

    .agents/skills/debugging/SKILL.md, line 523

    // BUG: Editing .env when the app reads from config.json

    .agents/skills/hostinger-deploy/SKILL.md, line 68

    grep -r "sk_live\|api_key\|password\|secret" --include="*.ts" --include="*.js" --include="*.env" || echo "Clean"

    .agents/skills/infra-deploy/SKILL.md, line 27

    cat .env.example # Document required vars

    Show more

    .agents/skills/infra-deploy/SKILL.md, line 206

    --env-file .env.production \

    src/config.ts, line 128

    apiKeys: process.env.API_KEYS?.split(',').map(k => k.trim()).filter(Boolean),

    src/code-execution/pii-tokenizer.ts, line 316

    const _piiEnabled = (process.env.PII_TOKENIZATION_ENABLED ?? '1') !== '0';

    src/code-execution/pii-tokenizer.ts, line 318

    const raw = (process.env.PII_TOKENIZATION_TYPES ?? '')

    src/middleware/authorization.ts, line 30

    const scopeMap = parseMapping(process.env.API_KEY_SCOPES);

    src/middleware/authorization.ts, line 31

    const identityMap = parseMapping(process.env.API_KEY_IDENTITIES);

    src/middleware/authorization.ts, line 32

    const defaultScopes = process.env.API_KEY_DEFAULT_SCOPES ?? '*';

    .agents/skills/git-workflow/SKILL.md, line 173

    2. NEVER commit .env files or secrets

    .dockerignore, line 21

    # Environment files

    .dockerignore, line 22

    .env

    .env.example, line 2

    # Copy this file to .env and update values as needed.

  • Agent instructions

    Pass

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

  • Obfuscation

    Pass

    No encoded or minified payload found.

  • 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 549f494a9e36. requests shell access. The manifest names this permission. install fetches a script from the network. accepts a host from input, with no fixed list in this file. reads a credential or environment file.

Date and source

Date checked:

View source

github.com

Commit graded: 549f494a9e363f40530149de324b8097de424230

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