Grades are a hygiene check, not a security guarantee.

Claude Code, Skill

Prompt Studio

Prompt engineering workbench with a Lean persona layer that cuts LLM output size, cost, and latency.

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 f220afc6501a, unchanged since the check below.

SECRETS_PATH_CREDENTIAL

Why this grade

  • SECRETS_PATH_CREDENTIAL Medium

    Mentions a credential store path (~/.ssh, id_rsa, .npmrc, .aws/credentials, credentials.json, .netrc).

    hooks/_lean_common.py, line 71 # path pointing at ~/.ssh/id_rsa; readers would leak it), caps read size,

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

    Note

    requests shell access. The manifest names this permission.

    PERMISSION_SHELL_DECLARED

    benchmarks/agentic/run.py, line 152

    return subprocess.run([shutil.which("git") or "git", *args], cwd=str(workdir),

    benchmarks/agentic/run.py, line 230

    subprocess.run(["taskkill", "/F", "/T", "/PID", str(proc.pid)],

    benchmarks/agentic/run.py, line 238

    p = subprocess.Popen([sys.executable, "-c", "import time; time.sleep(30)"],

    Show more

    benchmarks/agentic/run.py, line 323

    # open forever, so subprocess.run(timeout=) never fires and the worker freezes. Writing to a file

    benchmarks/agentic/run.py, line 328

    proc = subprocess.Popen(cmd, cwd=str(workdir), stdout=so, stderr=se,

    benchmarks/agentic/run.py, line 399

    try: return subprocess.run([shutil.which("claude"), "--version"], capture_output=True, text=True).stdout.strip()

    benchmarks/agentic/tasks.py, line 543

    proc = subprocess.Popen([node, str(srv)], cwd=str(workdir), env=env,

    skills/compress/scripts/compress.py, line 212

    result = subprocess.run(

  • Install and update

    Concern

    dependencies are not pinned.

    INSTALL_UNPINNED

    requirements.txt, line 11

    supermemory>=3.0.0

  • Network

    Concern

    can reach a host that is not written as a fixed address.

    NETWORK_NO_FIXED_HOST

    app/services/model_catalog.py, line 25

    resp = httpx.get(cfg.litellm_price_url, timeout=cfg.litellm_fetch_timeout)

    benchmarks/benchmark.py, line 62

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

    benchmarks/agentic/judge.py, line 72

    with urllib.request.urlopen(req, timeout=60) as r:

    Show more

    benchmarks/agentic/tasks.py, line 540

    with urllib.request.urlopen(r, timeout=4) as resp:

    frontend/lib/api.ts, line 23

    const r = await fetch(url, opts);

  • Secrets

    Concern

    reads a credential or environment file.

    SECRETS_ENV_READ SECRETS_PATH_CREDENTIAL SECRETS_PATH_DOTENV

    app/config.py, line 11

    env_file=".env",

    benchmarks/benchmark.py, line 82

    key = os.environ.get("ANTHROPIC_API_KEY")

    hooks/_lean_common.py, line 71

    # path pointing at ~/.ssh/id_rsa; readers would leak it), caps read size,

    Show more

    benchmarks/benchmark.py, line 129

    key = os.environ.get("OPENAI_API_KEY")

    benchmarks/benchmark.py, line 166

    key = os.environ.get("GEMINI_API_KEY") or os.environ.get("GOOGLE_API_KEY")

    benchmarks/agentic/complete.py, line 20

    Judge: claude-sonnet-4-6, key from ../../.env (shared with judge.py). ~$0.003/cell.

    benchmarks/agentic/complete.py, line 146

    if not key: sys.exit("no ANTHROPIC_API_KEY (.env or env)")

    benchmarks/agentic/judge.py, line 13

    Judge: claude-sonnet-4-6 via the Anthropic Messages API (key from ../../.env). Scores the SOURCE

    benchmarks/agentic/judge.py, line 43

    for line in (ROOT / ".env").read_text(encoding="utf-8").splitlines():

    benchmarks/agentic/judge.py, line 48

    return os.environ.get("ANTHROPIC_API_KEY")

    benchmarks/agentic/judge.py, line 177

    if not key: sys.exit("no ANTHROPIC_API_KEY (.env or env)")

    skills/compress/scripts/compress.py, line 46

    # developers on sensitive codebases cannot cross. detect.py already skips .env

    skills/compress/scripts/compress.py, line 190

    api_key = os.environ.get("ANTHROPIC_API_KEY")

  • 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 f220afc6501a. requests shell access. The manifest names this permission. dependencies are not pinned. 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: f220afc6501a727985d5687fa0ccc56270537c5c

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