Grades are a hygiene check, not a security guarantee.

MCP, MCP server

OmniGlyph

OmniGlyph, an MCP server listed in the PlugVet directory.

Compatibility: Not stated.

Grade C

One Medium finding. Read the findings before installing.

Graded by PlugVetRubric v2

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

PERMISSION_SHELL_UNDECLARED

Why this grade

  • PERMISSION_SHELL_UNDECLARED Medium

    Runs shell commands that the manifest or description does not mention.

    scripts/installed_smoke.py, line 25 mcp_output = subprocess.run(

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.

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

    Concern

    requests shell access. No manifest field names shell or command execution.

    PERMISSION_SHELL_UNDECLARED

    scripts/installed_smoke.py, line 25

    mcp_output = subprocess.run(

    scripts/installed_smoke.py, line 52

    return subprocess.run(command, text=True, capture_output=True, check=True, env=env).stdout

    docs/superpowers/plans/2026-04-30-logosgate-mvp.md, line 1191

    return subprocess.run(

    Show more

    docs/superpowers/plans/2026-07-05-output-guardrail-cli.md, line 68

    return subprocess.run(

    docs/superpowers/plans/2026-07-05-policy-pack-intent-guardrail.md, line 246

    init_result = subprocess.run([... "init-policy-pack", str(target), "--namespace", "private_cli", "--policy-id", "personal.cli", "--name", "CLI Policy"], check=False, capture_output

    docs/superpowers/plans/2026-07-05-policy-pack-intent-guardrail.md, line 247

    validate_result = subprocess.run([... "validate-policy-pack", str(target)], check=False, capture_output=True, text=True)

    docs/superpowers/plans/2026-07-05-policy-pack-intent-guardrail.md, line 248

    enforce_result = subprocess.run([... "enforce-intent", "example.review", "--policy-pack", str(target), "--actor-role", "admin", "--parameters", "{\"ticket\":\"123\"}"], check=False

    docs/superpowers/plans/2026-07-16-parameter-schema-fail-closed.md, line 387

    result = subprocess.run(

  • Install and update

    Pass

    No install-time script found, and dependencies are pinned or absent.

  • Network

    Note

    can reach localhost.

    NETWORK_LOCALHOST

    Dockerfile, line 9

    HEALTHCHECK --interval=30s --timeout=3s --start-period=5s --retries=3 CMD python -c "import urllib.request; urllib.request.urlopen('http://127.0.0.1:8000/api/v1/health')"

  • Secrets

    Note

    reads an environment variable.

    SECRETS_ENV_READ

    src/omniglyph/api.py, line 90

    expected = os.environ.get("OMNIGLYPH_API_TOKEN", "").strip()

  • 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 2d4053983de3. requests shell access. No manifest field names shell or command execution. can reach localhost. reads an environment variable.

Date and source

Date checked:

View source

github.com

Commit graded: 2d4053983de30849201918cb7bae5230dc47e8ca

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