Grades are a hygiene check, not a security guarantee.

Claude Code, Skill

Agent Skills

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 20/10/2026.

A collection of AI agent skills built for Hermes Agent, organised by domain.

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 ae671a22253e.

INSTALL_REMOTE_SCRIPT NETWORK_HOST_FROM_INPUT

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).

    productivity/marp-deck/SKILL.md, line 111 curl -fsSL https://raw.githubusercontent.com/iOfficeAI/OfficeCLI/main/install.sh | bash

  • NETWORK_HOST_FROM_INPUT Medium

    A file takes a URL or endpoint as input and has no fixed host list.

    research/source-tracker/scripts/source_db.py, line 154 with urllib.request.urlopen(request, timeout=timeout) as response:

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

    agent-ops/claude-plugin-converter/scripts/analyze.py, line 84

    "command": ("subprocess.run() in Python callback", "yes", "Translate ${CLAUDE_PLUGIN_ROOT}"),

    agent-ops/claude-plugin-converter/scripts/convert.py, line 279

    proc = subprocess.run(

    agent-ops/claude-plugin-converter/scripts/convert.py, line 796

    shutil.rmtree(p)

    Show more

    agent-ops/skill-maintainer/scripts/upstream_check.py, line 210

    r = subprocess.run(

    agent-ops/skill-maintainer/scripts/upstream_check.py, line 477

    r = subprocess.run(

    mlops/model-compare/scripts/compare.py, line 230

    shutil.rmtree(sandbox_dir, ignore_errors=True)

    mlops/model-compare/scripts/compare.py, line 261

    result = subprocess.run(

    mlops/model-compare/scripts/compare.py, line 854

    result = subprocess.run(

    plugins/lumen/skills/curator/scripts/adapters.py, line 495

    result = subprocess.run(

    productivity/file-organizer/scripts/organize.py, line 689

    return subprocess.run(command, cwd=test_path.parent).returncode

    productivity/file-organizer/scripts/test_organize.py, line 31

    shutil.rmtree(self.temp_dir, ignore_errors=True)

    productivity/file-organizer/scripts/test_organize.py, line 183

    shutil.rmtree(outside, ignore_errors=True)

    productivity/file-organizer/scripts/test_organize.py, line 234

    shutil.rmtree(temp_dir, ignore_errors=True)

  • Install and update

    Serious

    install fetches a script from the network.

    INSTALL_REMOTE_SCRIPT

    productivity/marp-deck/SKILL.md, line 111

    curl -fsSL https://raw.githubusercontent.com/iOfficeAI/OfficeCLI/main/install.sh | bash

    productivity/marp-deck/scripts/md2pptx-officecli.py, line 20

    curl -fsSL https://raw.githubusercontent.com/iOfficeAI/OfficeCLI/main/install.sh | bash

    productivity/marp-deck/README.md, line 70

    `curl -fsSL https://raw.githubusercontent.com/iOfficeAI/OfficeCLI/main/install.sh | bash`,

  • Network

    Serious

    accepts a host from input, with no fixed list in this file.

    NETWORK_HOST_FROM_INPUT

    research/source-tracker/scripts/source_db.py, line 154

    with urllib.request.urlopen(request, timeout=timeout) as response:

    research/source-tracker/scripts/url_health.py, line 62

    with urllib.request.urlopen(request, timeout=timeout) as response:

    web-scraping/website-scraping/scripts/recon.py, line 88

    with urllib.request.urlopen(req, timeout=timeout) as resp:

    Show more

    web-scraping/website-scraping/scripts/recon.py, line 300

    if not http.get("ok"):

    web-scraping/website-scraping/scripts/recon.py, line 301

    print(f" ✗ fetch failed: {http.get('error') or 'status ' + str(http.get('status'))}")

    web-scraping/website-scraping/scripts/recon.py, line 302

    if http.get("status"):

    web-scraping/website-scraping/scripts/recon.py, line 304

    if http.get("body"):

    web-scraping/website-scraping/scripts/recon.py, line 316

    if http.get("ok") or http.get("body"):

    web-scraping/website-scraping/scripts/recon.py, line 317

    a = analyse(http.get("body", b""), label="http")

    web-scraping/website-scraping/scripts/recon.py, line 328

    if args.save and http.get("body"):

    web-scraping/website-scraping/scripts/recon.py, line 332

    # Playwright fetch (optional)

    web-scraping/website-scraping/scripts/recon.py, line 370

    sys.exit(0 if (http.get("ok") or (pw and pw.get("ok"))) else 1)

  • Secrets

    Concern

    reads a credential or environment file.

    SECRETS_ENV_READ SECRETS_PATH_DOTENV

    creative/clips-studio/scripts/falvid.py, line 280

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

    creative/clips-studio/scripts/falvid.py, line 301

    if am and not os.environ.get("FAL_ADMIN_KEY"):

    creative/clips-studio/scripts/falvid.py, line 309

    if not os.environ.get("FAL_KEY"):

    Show more

    creative/clips-studio/scripts/falvid.py, line 339

    admin = os.environ.get("FAL_ADMIN_KEY")

    creative/clips-studio/scripts/falvid.py, line 689

    key = os.environ.get("FAL_KEY", "")

    creative/clips-studio/scripts/falvid.py, line 718

    key = os.environ.get("FAL_KEY", "")

    creative/image-studio/scripts/falgen.py, line 92

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

    creative/image-studio/scripts/falgen.py, line 113

    if am and not os.environ.get("FAL_ADMIN_KEY"):

    agent-ops/claude-plugin-converter/scripts/convert.py, line 610

    lines.append(f"- Set `{ev}` in `~/.hermes/.env`")

    agent-ops/hermes-onboarding/scripts/weekly_health_check.sh, line 8

    # Load env vars from .env (for any skill scripts that need them)

    agent-ops/hermes-onboarding/scripts/weekly_health_check.sh, line 9

    if [ -f ~/.hermes/.env ]; then

    agent-ops/hermes-onboarding/scripts/weekly_health_check.sh, line 14

    done < ~/.hermes/.env

    creative/clips-studio/scripts/falvid.py, line 277

    dropped in a file. The filename does NOT matter (users rarely use `.env`): the key is detected by

    creative/clips-studio/scripts/falvid.py, line 282

    exts = {".txt", ".env", ".cfg", ".ini", ".text", ""}

  • 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 ae671a22253e. can delete files. install fetches a script from the network. accepts a host from input, with no fixed list in this file. reads a credential or environment file.

Date and source

Date checked:

View source

github.com

Commit graded: ae671a22253ed3dfe81a96d8405aecd3fc9baec6

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