Grades are a hygiene check, not a security guarantee.

Claude Code, Skill

Open Skills

Reusable, inspectable skills for AI coding agents.

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.

Rescanned at commit d2a6d03462a1, unchanged since the check below.

OBFUSCATION_MINIFIED_PAYLOAD

Why this grade

  • OBFUSCATION_MINIFIED_PAYLOAD Medium

    Contains a very long line with almost no spaces in a script or style file.

    skills/headless-gemini/scripts/test-supervision.mjs, line 11 function bounded(executable,args,timeoutMs){return new Promise((resolve,reject)=>{const p=spawn(executable,args,{shell:false,windowsHide:true,stdio:['ignore','pipe','pipe']});let o

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

    install.mjs, line 373

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

    install.mjs, line 398

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

    install.mjs, line 408

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

    Show more

    skills/new-skill-creator/references/RENAME-CHECKLIST.md, line 50

    shutil.rmtree(p)

  • 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

    skills/headless-update-models/scripts/fetch-deepswe.mjs, line 44

    response = await fetch(URL, { signal: controller.signal, redirect: 'error' });

    catalog.json, line 3623

    "description": "Expand a vague gap into concrete questions + named source candidates via a delegated sub-agent - caller sees only the proposed pair for confirm/edit/refuse, never t

    catalog.json, line 3634

    "why": "When the expansion needs a single noisy data-fetch (Grep/WebFetch/MCP) on the proposed source"

    Show more

    catalog.json, line 3731

    "description": "Prime the calling agent with high-signal context from large source surfaces (multiple files, packages, folders) via parallel delegated sub-agents. Sub-agents absorb

    catalog.yon, line 69

    @META id=prime-expand | family=priming | visibility=public | protocol=yes | profile=exec | description="Expand a vague gap into concrete questions + named source candidates via a d

    catalog.yon, line 71

    @META id=prime-sweep | family=priming | visibility=public | protocol=yes | profile=exec | description="Prime the calling agent with high-signal context from large source surfaces (

    skills/prime-expand/SKILL.md, line 3

    description: Expand a vague gap into concrete questions + named source candidates via a delegated sub-agent - caller sees only the proposed pair for confirm/edit/refuse, never the

    skills/prime-expand/SKILL.md, line 12

    why: "When the expansion needs a single noisy data-fetch (Grep/WebFetch/MCP) on the proposed source"

  • Secrets

    Concern

    reads a credential or environment file.

    SECRETS_PATH_DOTENV

    skills/github-sync/SKILL.md, line 37

    Always route unrelated or unsafe-to-stage work into `Excluded Changes`: worktree/submodule dirty markers (`.claude/worktrees/*`), generated artifacts not requested for commit, unre

    skills/github-sync/SKILL.md, line 102

    - NEVER stage files not listed in the approved plan, or `.env` files, binaries, or debug artifacts.

    skills/github-sync/protocol.yon, line 13

    @MAP name=ExcludedAlways | pairs=["worktree-submodule-markers"->"e.g. .claude/worktrees/*","generated-artifacts"->"not requested for commit","unrelated-edits"->"local edits outside

    Show more

    skills/github-sync/protocol.yon, line 55

    @RULE rid=rule:no-unlisted-files | lvl=MUST_NOT | when="staging" | then="stage files not listed in the approved commit plan, or .env files, binaries, or debug artifacts"

  • Agent instructions

    Pass

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

  • Obfuscation

    Concern

    contains a minified payload.

    OBFUSCATION_MINIFIED_PAYLOAD

    skills/headless-gemini/scripts/test-supervision.mjs, line 11

    function bounded(executable,args,timeoutMs){return new Promise((resolve,reject)=>{const p=spawn(executable,args,{shell:false,windowsHide:true,stdio:['ignore','pipe','pipe']});let o

    skills/yon-read/references/type-system.md, line 1

    # YON Type System & References - Quick Reference

  • 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 d2a6d03462a1. can delete files. can reach a host that is not written as a fixed address. reads a credential or environment file. contains a minified payload.

Date and source

Date checked:

View source

github.com

Commit graded: d2a6d03462a1529b08bcd11e67ab86e2a1f866dc

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