Grades are a hygiene check, not a security guarantee.

Claude Code, Skill

Claude Codex Skills Assembly

Reusable agent skills, deterministic activation, safety hooks, and installers for Claude Code and OpenAI Codex, with an agentskills.io-compatible skill surface.

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).

    scripts/validate.py, line 1055 if name in {".netrc", ".npmrc", "credentials.json", "id_dsa", "id_ecdsa", "id_ed25519", "id_rsa"}:

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

    Note

    requests shell access. The manifest names this permission.

    PERMISSION_SHELL_DECLARED

    install.py, line 1100

    result = subprocess.run(

    install.py, line 1419

    result = subprocess.run(

    hooks/merge-guard.py, line 52

    p = subprocess.run(

    Show more

    scripts/validate.py, line 142

    top_level = subprocess.run(

    scripts/validate.py, line 158

    tracked = subprocess.run(

    skills/delivery-loop/scripts/browser-suite-lease.py, line 151

    completed = subprocess.run(

    skills/delivery-loop/scripts/delivery-state.py, line 42

    return subprocess.run(

  • Install and update

    Pass

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

  • Network

    Pass

    No network call found.

  • Secrets

    Concern

    reads a credential or environment file.

    SECRETS_PATH_CREDENTIAL SECRETS_PATH_DOTENV

    scripts/validate.py, line 1053

    if name.startswith(".env") and name not in {".env.example", ".env.sample", ".env.template"}:

    scripts/validate.py, line 1055

    if name in {".netrc", ".npmrc", "credentials.json", "id_dsa", "id_ecdsa", "id_ed25519", "id_rsa"}:

    routing/skill-rules.json, line 404

    "**/.env*",

    Show more

    skills/security-review/SKILL.md, line 31

    - Secrets live in env or a secret store, scoped per environment, never echoed to logs. Hardcoded fallbacks and committed `.env` files are blockers. Rotate on departure or runner re

    skills/security-review/references/checklist.md, line 9

    - `.env*` and config files are never committed; check `.gitignore`. Logger redaction covers every key the app handles.

  • 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 1c3f69f352a8. requests shell access. The manifest names this permission. reads a credential or environment file.

Date and source

Date checked:

View source

github.com

Commit graded: 1c3f69f352a8353d6c24e00ebee036bc98e98fee

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