Grades are a hygiene check, not a security guarantee.

Claude Code, Skill

LetUenforskills

LetUenforskills, a skill listed in the PlugVet directory.

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 89a0bc49354d, unchanged since the check below.

PERMISSION_SHELL_UNDECLARED

Why this grade

  • PERMISSION_SHELL_UNDECLARED Medium

    Runs shell commands that the manifest or description does not mention.

    scripts/local_bridge.py, line 190 subprocess.Popen(["open", str(path)])

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

    requests shell access. No manifest field names shell or command execution. can delete files.

    PERMISSION_SHELL_UNDECLARED PERMISSION_DELETE_FILES

    scripts/local_bridge.py, line 190

    subprocess.Popen(["open", str(path)])

    scripts/local_bridge.py, line 192

    subprocess.Popen(["xdg-open", str(path)])

    scripts/local_bridge.py, line 243

    subprocess.Popen(["open", uri])

    Show more

    scripts/local_bridge.py, line 245

    subprocess.Popen(["xdg-open", uri])

    scripts/local_bridge.py, line 253

    completed = subprocess.run(

    scripts/local_bridge.py, line 269

    subprocess.Popen([str(exe), uri], stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL)

    scripts/local_bridge.py, line 391

    run_proc = subprocess.run(run_cmd, cwd=ROOT, env=env, text=True, capture_output=True, timeout=900)

    scripts/local_bridge.py, line 410

    export_proc = subprocess.run(export_cmd, cwd=ROOT, env=env, text=True, capture_output=True, timeout=300)

  • 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

    scripts/local_bridge.py, line 482

    with urllib.request.urlopen(request, timeout=45) as response:

    scripts/local_bridge.py, line 519

    with urllib.request.urlopen(request, timeout=45) as response:

    site/script.js, line 341

    const startResponse = await fetch(`${bridgeBaseUrl}/api/analyze/jobs`, {

    Show more

    site/script.js, line 356

    const pollResponse = await fetch(`${bridgeBaseUrl}/api/analyze/jobs/${encodeURIComponent(startPayload.job_id)}`);

    site/script.js, line 375

    const response = await fetch(`${bridgeBaseUrl}/api/analyze/run`, {

    site/script.js, line 574

    const response = await fetch('http://localhost:8765/api/models/test', {

    site/script.js, line 1110

    const response = await fetch('./cinema-data.json', { cache: 'no-store' });

    site/script.js, line 1399

    const response = await fetch('../cinema/cinema-data.json', { cache: 'no-store' });

    site/script.js, line 1549

    const response = await fetch('../cinema/cinema-data.json', { cache: 'no-store' });

    src/asa/vault_exporter.py, line 153

    const response = await fetch('http://127.0.0.1:8765/api/obsidian/open', {{

  • Secrets

    Concern

    reads a credential or environment file.

    SECRETS_PATH_DOTENV

    site/script.js, line 532

    se}\n api_key_env: ${config.env}\n\n# .env or local bridge session\n${config.env}=

    src/asa/runtime.py, line 20

    from .env import load_dotenv

    src/asa/runtime.py, line 33

    load_dotenv(config.path.parent / ".env")

    Show more

    .gitignore, line 1

    .env

    README.md, line 60

    cp .env.example .env

    README.md, line 78

    The default config uses `mock`. For real multi-agent calls, copy one provider config and set the matching key in `.env` or your shell.

    README.md, line 93

    notepad .env

    README.md, line 126

    Then open `http://localhost:4173/settings/models/`. The bridge does not persist keys. For CLI runs, store keys in `.env` using the mapped environment variable.

  • 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.

Get the full report on this tool, £49

Note

Hygiene check of commit 89a0bc49354d. requests shell access. No manifest field names shell or command execution. can delete files. can reach a host that is not written as a fixed address. reads a credential or environment file.

Date and source

Date checked:

View source

github.com

Commit graded: 89a0bc49354dcf7cc9717995ae2393f20e5475ed

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