Grades are a hygiene check, not a security guarantee.

Claude Code, Skill

Make Skill

Create, audit and publish Agent Skills and Claude Code plugins against one enforced repository standard.

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.

SECRETS_PATH_CREDENTIAL

Why this grade

  • SECRETS_PATH_CREDENTIAL Medium

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

    plugins/make-skill/skills/make-skill/scripts/audit_skill.py, line 287 r"credential|credentials|\.env|id_rsa|id_ed25519|private[_-]?key)(?:$|[._/-])")

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

    can delete files.

    PERMISSION_DELETE_FILES

    bin/make-skill.js, line 105

    fs.rmSync(dest, { recursive: true, force: true });

    .github/workflows/validate.yml, line 635

    subprocess.run(

    CONTRIBUTING.md, line 77

    r = subprocess.run(['bash','-c',s['run']], capture_output=True, text=True, env=env)

  • 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

    plugins/make-skill/skills/make-skill/references/enterprise.md, line 63

    4. **Grep for network access** (`http`, `requests.get`, `urllib`, `curl`, `fetch`)

  • Secrets

    Concern

    reads a credential or environment file.

    SECRETS_ENV_READ SECRETS_PATH_CREDENTIAL SECRETS_PATH_DOTENV

    plugins/make-skill/skills/make-skill/scripts/audit_skill.py, line 151

    name = os.environ.get("MAKE_SKILL_TOKENIZER") or DEFAULT_ENCODING

    plugins/make-skill/skills/make-skill/scripts/audit_skill.py, line 162

    if os.environ.get("MAKE_SKILL_TOKENIZER"):

    plugins/make-skill/skills/make-skill/scripts/audit_skill.py, line 287

    r"credential|credentials|\.env|id_rsa|id_ed25519|private[_-]?key)(?:$|[._/-])")

    Show more

    .gitignore, line 8

    # agent-sync - local credentials and run state, never committed

    .gitignore, line 13

    # untracked-but-unignored .env at a sibling's repo root, one `git add -A`

    .gitignore, line 14

    # away from a public repository. The hole was open in all nine.

    .gitignore, line 15

    .env

    .gitignore, line 17

    !.env.example

    docs/AGENT_SYNC.md, line 22

    - credentials read from `.env.agent-sync` in sshlg-skills - gitignored, never committed

    plugins/make-skill/skills/make-skill/references/distribution.md, line 441

    - **An undeclared secret.** A `.env`, a `*token*` fixture, an `id_rsa`,

  • 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.

Note

Hygiene check of commit a0ba42690ee7. can delete files. 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: a0ba42690ee700100bd43803043eecd23a057951

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