Grades are a hygiene check, not a security guarantee.

Claude Code, Skill

skills

Reusable agent skills in the SKILL.md format, compatible with OpenAI Codex, Claude Code, and other agents that follow that convention.

Compatibility: Not stated.

Grade C

One Medium finding. Read the report 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.

    skills/explainer-video/templates/build.py, line 21 subprocess.run(["ffmpeg", "-y", "-loglevel", "error", *args], check=True)

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

    skills/explainer-video/templates/build.py, line 21

    subprocess.run(["ffmpeg", "-y", "-loglevel", "error", *args], check=True)

    skills/explainer-video/templates/gen_cues.py, line 24

    voice = float(subprocess.check_output(["ffprobe", "-v", "error", "-show_entries", "format=duration", "-of", "csv=p=0", f"voice/{s}.mp3"]))

  • Install and update

    Pass

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

  • Network

    Concern

    can reach a host that is not written as a fixed address.

    NETWORK_NO_FIXED_HOST

    .agents/skills/tdd/mocking.md, line 44

    getUser: (id) => fetch(`/users/${id}`),

    .agents/skills/tdd/mocking.md, line 45

    getOrders: (userId) => fetch(`/users/${userId}/orders`),

    .agents/skills/tdd/mocking.md, line 46

    createOrder: (data) => fetch('/orders', { method: 'POST', body: data }),

    Show more

    .agents/skills/tdd/mocking.md, line 51

    fetch: (endpoint, options) => fetch(endpoint, options),

    skills/explainer-video/templates/tts.py, line 31

    res = json.load(urllib.request.urlopen(req, timeout=120))

  • Secrets

    Concern

    reads a credential or environment file.

    SECRETS_ENV_READ SECRETS_PATH_DOTENV

    .agents/skills/tdd/mocking.md, line 32

    const client = new StripeClient(process.env.STRIPE_KEY);

    .agents/skills/wizard/template.sh, line 26

    ENV_FILE="${ENV_FILE:-.env}"

    .agents/skills/wizard/template.sh, line 98

    # ask KEY "Prompt" reads a value into $KEY. Offers the existing .env value as

    Show more

    skills/granola-transcripts/SKILL.md, line 18

    python3 -c 'import os; print("GRANOLA_API_KEY: " + ("set" if os.getenv("GRANOLA_API_KEY") else "missing"))'

    skills/granola-transcripts/scripts/granola.py, line 29

    key = os.environ.get("GRANOLA_API_KEY")

    .agents/skills/ask-matt/SKILL.md, line 83

    - **`/wizard`** is for the steps only a **human** can take: provisioning infrastructure, setting up credentials or CI secrets, clicking through an unfamiliar third-party dashboard,

    .agents/skills/wizard/SKILL.md, line 8

    A **wizard** is a bash script that walks a human, step by step, through a manual procedure that's tedious to do by hand and tedious to re-explain to an AI every time. It opens each

    .agents/skills/wizard/SKILL.md, line 10

    The delightful UX is already solved by [template.sh](template.sh): stage-by-stage progress, confirmation gates, cross-platform URL opening (including WSL), hidden secret entry, ide

    .agents/skills/wizard/SKILL.md, line 20

    - For setup: `.env`, `.env.example`, `.env.*`, `README`, `docker-compose*`, framework config, and `.github/workflows/*` (every `secrets.*` / `vars.*` reference is a value the wizar

    .agents/skills/wizard/SKILL.md, line 25

    **Done when:** every stage is named in order, and for each captured value you know (a) where the human gets it, (b) where it's written (`.env`, a GitHub secret, both, or nowhere; s

  • 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 49fab7f4cb5b. requests shell access. No manifest field names shell or command execution. can reach a host that is not written as a fixed address. reads a credential or environment file.

Date and source

Date checked:

View source

github.com

Commit graded: 49fab7f4cb5b5e8b5a156391b50498eb3ca5f144

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