Grades are a hygiene check, not a security guarantee.

Claude Code, Skill

Ai Agent Skills

Ai Agent Skills has PlugVet grade B (Minor notes only) from our automated hygiene checks. Finding: contains a call that can delete files. This is a hygiene check, not a security audit or a guarantee. Graded on 16/10/2026.

Universal skill installer and package manager for AI coding agents.

Compatibility: Not stated.

Grade B

Minor issues only, no Medium or High. Worth a quick look at the findings below 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 6d95c788aa22, unchanged since the check below.

PERMISSION_DELETE_FILES NETWORK_NO_FIXED_HOST SECRETS_PATH_DOTENV SECRETS_ENV_READ OBFUSCATION_FILE_OVER_READ_CAP

Why this grade

  • PERMISSION_DELETE_FILES Low

    Contains a call that can delete files.

    test.js, line 204 fs.rmSync(parentDir, { recursive: true, force: true });

  • NETWORK_NO_FIXED_HOST Low

    Makes a network call whose host is not written as a fixed address.

    skills/verification-agent/references/protocol.md, line 39 "fetchedVia": "curl (fetch returned 403)", // how, incl. fallbacks

  • SECRETS_PATH_DOTENV Low

    Mentions a .env file.

    skills/best-practices/references/before-after-examples.md, line 472 1. add Google OAuth credentials to .env.example

  • SECRETS_ENV_READ Note

    Reads an environment variable whose name contains KEY, SECRET, TOKEN, PASSWORD or CREDENTIAL.

    skills/llm-application-dev/SKILL.md, line 67 const openai = new OpenAI({ apiKey: process.env.OPENAI_API_KEY });

  • OBFUSCATION_FILE_OVER_READ_CAP Note

    A file was over the read cap and was not fully read.

    cli.js, line 1 #!/usr/bin/env node

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

    test.js, line 204

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

    test.js, line 296

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

    test.js, line 639

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

    Show more

    test.js, line 670

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

    test.js, line 686

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

    test.js, line 881

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

    test.js, line 1013

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

    test.js, line 1071

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

  • 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/verification-agent/references/protocol.md, line 39

    "fetchedVia": "curl (fetch returned 403)", // how, incl. fallbacks

    skills/verification-agent/scripts/lib/providers.mjs, line 54

    * a curl fallback is attempted once on 403/406/429 or a transport error. This is a real and

    skills/verification-agent/scripts/lib/providers.mjs, line 62

    const res = await fetch(url, { headers: h, signal: ctl, redirect: 'follow' });

    Show more

    skills/verification-agent/scripts/lib/providers.mjs, line 67

    via = `curl (fetch returned ${res.status})`;

    skills/verification-agent/scripts/lib/providers.mjs, line 70

    via = `curl (fetch failed: ${err.message})`;

    skills/verification-agent/scripts/lib/providers.mjs, line 82

    throw new Error(`both fetch and curl failed for ${url}: ${err.message}`);

  • Secrets

    Concern

    reads a credential or environment file.

    SECRETS_ENV_READ SECRETS_PATH_DOTENV

    skills/best-practices/references/before-after-examples.md, line 472

    1. add Google OAuth credentials to .env.example

    skills/best-practices/references/before-after-examples.md, line 654

    - environment variables needed (.env.example reference)

    skills/llm-application-dev/SKILL.md, line 67

    const openai = new OpenAI({ apiKey: process.env.OPENAI_API_KEY });

    Show more

    skills/llm-application-dev/SKILL.md, line 85

    const anthropic = new Anthropic({ apiKey: process.env.ANTHROPIC_API_KEY });

  • Agent instructions

    Pass

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

  • Obfuscation

    Note

    a file was over the read cap and was not fully read.

    OBFUSCATION_FILE_OVER_READ_CAP

    cli.js, line 1

    #!/usr/bin/env node

    skills.json, line 1

    {

  • 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 6d95c788aa22. can delete files. can reach a host that is not written as a fixed address. reads a credential or environment file. a file was over the read cap and was not fully read.

Date and source

Date checked:

View source

github.com

Commit graded: 6d95c788aa22ce39a4807b9a4c31c758a2036dc6

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