Grades are a hygiene check, not a security guarantee.

Claude Code, Skill

10xProductivity

Personal AI assistant for work inside corporate constraints, built on coding agents and the tools, sessions, and permissions you already have.

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 9a7da40bc798, 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.

    runtime/host.py, line 173 proc = subprocess.run(cmd, cwd=str(root), env={**os.environ, **(extra_env or {})}, capture_output=True, text=True)

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.

    PERMISSION_SHELL_UNDECLARED

    runtime/host.py, line 173

    proc = subprocess.run(cmd, cwd=str(root), env={**os.environ, **(extra_env or {})}, capture_output=True, text=True)

    runtime/agent_clients/claude.py, line 98

    proc = subprocess.Popen(

    runtime/agent_clients/cursor.py, line 162

    proc = subprocess.Popen(

    Show more

    tool_connections/google-ai-mode/google_ai_mode.py, line 105

    result = subprocess.run(["pgrep", "-f", profile_str], capture_output=True, text=True)

    tool_connections/google-ai-mode/google_ai_mode.py, line 113

    ps = subprocess.run(

    tool_connections/google-ai-mode/google_ai_mode.py, line 131

    result = subprocess.run(

    tool_connections/google-ai-mode/google_ai_mode.py, line 160

    subprocess.run(["kill", str(pid)], check=False)

    tool_connections/google-ai-mode/google_ai_mode.py, line 208

    subprocess.Popen(

  • Install and update

    Concern

    dependencies are not pinned.

    INSTALL_UNPINNED

    requirements.txt, line 15

    pytest

  • Network

    Concern

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

    NETWORK_NO_FIXED_HOST

    runtime/scheduling/standup_prep.py, line 122

    with urllib.request.urlopen(req, context=_slack_context(), timeout=25) as resp:

    tool_connections/google-ai-mode/google_ai_mode.py, line 93

    with urllib.request.urlopen(f"http://127.0.0.1:{port}/json/version", timeout=1) as resp:

    tool_connections/google-drive/gdrive_server.py, line 110

    with urllib.request.urlopen(

    Show more

    tool_connections/google-drive/sso.py, line 56

    with urllib.request.urlopen(req, context=ctx, timeout=8) as r:

    tool_connections/grafana/sso.py, line 44

    with urllib.request.urlopen(req, context=ctx, timeout=8) as r:

    tool_connections/linkedin/sso.py, line 62

    const r = await fetch('/voyager/api/me', {{

    tool_connections/m365-copilot-search/sso.py, line 56

    with urllib.request.urlopen(req, context=ctx, timeout=8) as r:

    tool_connections/microsoft-teams/sso.py, line 45

    with urllib.request.urlopen(req, context=ctx, timeout=8) as r:

    tool_connections/miro/read_miro.py, line 62

    with urllib.request.urlopen(req, context=ssl_ctx(), timeout=60) as resp:

  • Secrets

    Concern

    reads a credential or environment file.

    SECRETS_PATH_DOTENV

    .cursor/hooks/check-git-author.sh, line 9

    # The banned term is loaded from .env (gitignored) so it never appears as a

    .cursor/hooks/check-git-author.sh, line 13

    ENV_FILE="$REPO_ROOT/.env"

    .cursor/hooks/check-git-author.sh, line 15

    # Load BANNED_TERM from .env

    Show more

    runtime/env.py, line 26

    load_dotenv(dotenv_path=root / ".env", override=False)

    runtime/env.py, line 27

    load_dotenv(dotenv_path=private_dir() / ".env", override=False)

    runtime/env.py, line 28

    load_dotenv(dotenv_path=Path.cwd() / ".env", override=False)

    runtime/host.py, line 18

    from .env import load_environment, repo_root, tmp_dir, truthy_env

    runtime/replies.py, line 9

    from .env import load_environment

  • 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 9a7da40bc798. requests shell access. No manifest field names shell or command execution. 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: 9a7da40bc798e4e3fe91b10770cf0fcc13cf0886

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