Grades are a hygiene check, not a security guarantee.

Claude Code, Skill

Ai Agent Skills

Ai Agent Skills has PlugVet grade D (Two or more medium findings, or a high) from our automated hygiene checks. Main finding: fetches a script from the network and runs it (a pipe to a shell, or an install hook with a URL). This is a hygiene check, not a security audit or a guarantee. Graded on 18/10/2026.

Ai Agent Skills, a skill listed in the PlugVet directory.

Compatibility: Not stated.

Grade D

Two or more Medium findings, or a High finding. Only try it in a sandbox.

Graded by PlugVetRubric v2

Not a guarantee. A hygiene check of the source at the commit shown, not a security audit.

Rescanned at commit a0c9d4912484, unchanged since the check below.

INSTALL_REMOTE_SCRIPT

Why this grade

  • INSTALL_REMOTE_SCRIPT High

    Fetches a script from the network and runs it (a pipe to a shell, or an install hook with a URL).

    skills/autonomous-ai-agents/hermes-agent/SKILL.md, line 48 curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash

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.

If you think this grade is wrong, email [email protected] with the entry link and your evidence. We aim to acknowledge within two working days and decide within seven. If we confirm an error, we aim to correct it within 24 hours of confirming it. These are aims, not guarantees.

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

    scripts/install.py, line 61

    # Enable ANSI escape codes on Windows 10+ by calling os.system('')

    scripts/install.py, line 64

    os.system("")

    scripts/install.py, line 501

    result = subprocess.run(

    Show more

    scripts/release.py, line 69

    result = subprocess.run(

    scripts/skills-api.py, line 248

    shutil.rmtree(target_dir)

    skills/creative/ascii-video/references/architecture.md, line 700

    pipe = subprocess.Popen(cmd, stdin=subprocess.PIPE,

    skills/creative/ascii-video/references/architecture.md, line 726

    subprocess.run(["ffmpeg", "-y", "-f", "concat", "-safe", "0", "-i", concat_path,

    skills/creative/ascii-video/references/inputs.md, line 11

    subprocess.run(["ffmpeg", "-y", "-i", input_path, "-ac", "1", "-ar", "22050",

    skills/creative/ascii-video/references/inputs.md, line 106

    pipe = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.DEVNULL)

    skills/creative/ascii-video/references/optimization.md, line 647

    shutil.rmtree(segments_dir)

    skills/creative/ascii-video/references/optimization.md, line 653

    os.remove(wav)

    skills/creative/ascii-video/references/optimization.md, line 658

    os.remove(log)

    skills/creative/ascii-video/references/optimization.md, line 663

    # os.remove(cache)

  • Install and update

    Serious

    install fetches a script from the network. The docs document an installer that pipes a download into a shell.

    INSTALL_REMOTE_SCRIPT INSTALL_DOCUMENTED_INSTALLER

    skills/autonomous-ai-agents/hermes-agent/SKILL.md, line 48

    curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash

    skills/mlops/huggingface-hub/SKILL.md, line 22

    * **Installation:** `curl -LsSf https://hf.co/cli/install.sh | bash -s`

    skills/mlops/training/axolotl/references/other.md, line 310

    curl -LsSf https://astral.sh/uv/install.sh | sh

    Show more

    skills/mlops/training/unsloth/references/llms-txt.md, line 188

    curl -fsSL https://ollama.com/install.sh | sh

    skills/mlops/training/unsloth/references/llms-txt.md, line 1263

    curl -fsSL https://ollama.com/install.sh | sh

    skills/mlops/training/unsloth/references/llms-txt.md, line 3543

    curl -LsSf https://astral.sh/uv/install.sh | sh && source $HOME/.local/bin/env

    skills/mlops/training/unsloth/references/llms-txt.md, line 3754

    curl -fsSL https://ollama.com/install.sh | sh

    skills/mlops/training/unsloth/references/llms-txt.md, line 3975

    curl -fsSL https://ollama.com/install.sh | sh

    skills/mlops/training/unsloth/references/llms-txt.md, line 4475

    curl -fsSL https://ollama.com/install.sh | sh

    skills/mlops/training/unsloth/references/llms-txt.md, line 4594

    curl -fsSL https://ollama.com/install.sh | sh

    skills/mlops/training/unsloth/references/llms-txt.md, line 5291

    curl -fsSL https://ollama.com/install.sh | sh

    skills/mlops/training/unsloth/references/llms-txt.md, line 5927

    curl -fsSL https://ollama.com/install.sh | sh

    skills/mlops/training/unsloth/references/llms-txt.md, line 7141

    curl -fsSL https://ollama.com/install.sh | sh

    skills/mlops/training/unsloth/references/llms-txt.md, line 7814

    curl -fsSL https://ollama.com/install.sh | sh

    skills/mlops/training/unsloth/references/llms-txt.md, line 11481

    curl -fsSL https://ollama.com/install.sh | sh

    skills/social-media/xurl/SKILL.md, line 64

    curl -fsSL https://raw.githubusercontent.com/xdevplatform/xurl/main/install.sh | bash

  • Network

    Concern

    can reach a host that is not written as a fixed address. can reach asciified.thelicato.io. The description does not name that host. can reach ascii.co.uk. The description does not name that host. can reach api.github.com. The description does not name that host. can reach example.com. The description does not name that host. can reach raw.githubusercontent.com. The description does not name that host. can reach api.telegram.org. The description does not name that host. can reach www.browserbase.

    NETWORK_NO_FIXED_HOST NETWORK_UNNAMED_HOST NETWORK_NAMED_HOST

    scripts/create-labels.sh, line 22

    curl -s -X POST \

    scripts/quality-dashboard.py, line 477

    requests.post(url, json=data, timeout=10)

    scripts/release.py, line 382

    response = requests.post(url, json=data, timeout=10)

    Show more

    skills/creative/ascii-art/SKILL.md, line 68

    curl -s "https://asciified.thelicato.io/api/v2/ascii?text=Hello+World"

    skills/creative/ascii-art/SKILL.md, line 71

    curl -s "https://asciified.thelicato.io/api/v2/ascii?text=Hello&font=Slant"

    skills/creative/ascii-art/SKILL.md, line 72

    curl -s "https://asciified.thelicato.io/api/v2/ascii?text=Hello&font=Doom"

    skills/creative/ascii-art/SKILL.md, line 73

    curl -s "https://asciified.thelicato.io/api/v2/ascii?text=Hello&font=Star+Wars"

    skills/creative/ascii-art/SKILL.md, line 74

    curl -s "https://asciified.thelicato.io/api/v2/ascii?text=Hello&font=3-D"

    skills/creative/comfyui/SKILL.md, line 107

    curl -s http://127.0.0.1:8188/system_stats 2>/dev/null && echo "server: running"

    skills/creative/comfyui/SKILL.md, line 405

    curl -s http://127.0.0.1:8188/system_stats # health check

    skills/creative/comfyui/SKILL.md, line 503

    curl -X POST "http://127.0.0.1:8188/upload/image" \

    skills/creative/comfyui/SKILL.md, line 508

    curl -X POST "https://cloud.comfy.org/api/upload/image" \

    skills/creative/comfyui/SKILL.md, line 538

    curl -s http://127.0.0.1:8188/queue | python3 -m json.tool

    skills/creative/comfyui/SKILL.md, line 539

    curl -X POST http://127.0.0.1:8188/queue -d '{"clear": true}' # cancel pending

    skills/creative/comfyui/SKILL.md, line 540

    curl -X POST http://127.0.0.1:8188/interrupt # cancel running

    skills/creative/comfyui/SKILL.md, line 541

    curl -X POST http://127.0.0.1:8188/free \

  • Secrets

    Concern

    reads a credential or environment file.

    SECRETS_ENV_READ SECRETS_PATH_DOTENV

    scripts/quality-dashboard.py, line 84

    self.token = token or os.getenv('GITHUB_TOKEN')

    scripts/quality-dashboard.py, line 459

    bot_token = os.getenv('TELEGRAM_BOT_TOKEN')

    scripts/release.py, line 365

    bot_token = os.getenv('TELEGRAM_BOT_TOKEN')

    Show more

    skills/addyosmani/ci-cd-and-automation/SKILL.md, line 279

    .env.example → Committed (template for developers)

    skills/addyosmani/ci-cd-and-automation/SKILL.md, line 280

    .env → NOT committed (local development)

    skills/addyosmani/ci-cd-and-automation/SKILL.md, line 281

    .env.test → Committed (test environment, no real secrets)

    skills/addyosmani/context-engineering/SKILL.md, line 70

    - Never commit .env files or secrets

    skills/addyosmani/documentation-and-adrs/SKILL.md, line 207

    3. Set up environment: `cp .env.example .env`

    skills/addyosmani/security-and-hardening/SKILL.md, line 86

    secret: process.env.SESSION_SECRET, // From environment, not code

    skills/addyosmani/security-and-hardening/SKILL.md, line 167

    const API_KEY = process.env.STRIPE_API_KEY;

    skills/addyosmani/security-and-hardening/SKILL.md, line 271

    .env files:

    skills/addyosmani/security-and-hardening/SKILL.md, line 272

    ├── .env.example → Committed (template with placeholder values)

    skills/addyosmani/security-and-hardening/SKILL.md, line 273

    ├── .env → NOT committed (contains real secrets)

    skills/autonomous-ai-agents/hermes-agent/SKILL.md, line 929

    return bool(os.getenv("EXAMPLE_API_KEY"))

    skills/devops/tinyfish-integration/scripts/tinyfish_search.py, line 14

    return bool(os.getenv("TINYFISH_API_KEY"))

    skills/devops/tinyfish-integration/scripts/tinyfish_search.py, line 37

    api_key = os.getenv("TINYFISH_API_KEY")

  • Agent instructions

    Pass

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

  • Obfuscation

    Note

    the file cap was reached before every file was read.

    OBFUSCATION_FILE_CAP_REACHED

    skills/github/github-pr-workflow/templates/pr-body-bugfix.md, line 1

    ## Bug Description

  • 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 a0c9d4912484. can delete files. install fetches a script from the network. The docs document an installer that pipes a download into a shell. can reach a host that is not written as a fixed address. can reach asciified.thelicato.io. The description does not name that host. can reach ascii.co.uk. The description does not name that host. can reach api.github.com. The description does not name that host. can reach example.com. The description does not name that host. can reach raw.githubusercontent.com. The description does not name that host. can reach api.telegram.org. The description does not name that host. can reach www.browserbase. reads a credential

Date and source

Date checked:

View source

github.com

Commit graded: a0c9d49124849ba3de5d87b197c675c0176d7d04

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