Grades are a hygiene check, not a security guarantee.

Claude Code, Plugin

Claude Model Pilot

Suggest models and reasoning effort while preserving task continuity

Compatibility: Not stated.

Grade D

Two or more Medium findings, or a High. 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.

PERMISSION_SHELL_UNDECLARED SECRETS_PATH_CREDENTIAL

Why this grade

  • PERMISSION_SHELL_UNDECLARED Medium

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

    scripts/benchmark.py, line 174 self.proc=subprocess.Popen(cmd,cwd=cwd,env=env,stdin=subprocess.PIPE,stdout=subprocess.PIPE,stderr=subprocess.PIPE,text=True,bufsize=1)

  • SECRETS_PATH_CREDENTIAL Medium

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

    docs/validation.md, line 17 Two isolated tests of the host's generic sensitive configuration found a plaintext `.credentials.json` fallback under restricted Keychain access and an empty-value update that did

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

    requests shell access. No manifest field names shell or command execution.

    PERMISSION_SHELL_UNDECLARED

    scripts/benchmark.py, line 174

    self.proc=subprocess.Popen(cmd,cwd=cwd,env=env,stdin=subprocess.PIPE,stdout=subprocess.PIPE,stderr=subprocess.PIPE,text=True,bufsize=1)

    scripts/credential-smoke.py, line 67

    r = subprocess.run([sys.executable, '-c', PROGRAM], cwd=ROOT, text=True,

    scripts/evaluate-advice.py, line 30

    p=subprocess.run(['node','--input-type=module','-e',BRID

    Show more

    scripts/live-eval.py, line 96

    proc = subprocess.Popen(cmd, cwd=cwd, env=env, stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True, bufsize=1)

  • Install and update

    Pass

    No install-time script found, and dependencies are pinned or absent.

  • Network

    Concern

    can reach api.typesafe.ai. The description does not name that host. can reach a host that is not written as a fixed address.

    NETWORK_NO_FIXED_HOST NETWORK_UNNAMED_HOST

    hooks/register.js, line 149

    const request = $.http.fetch('https://api.typesafe.ai/v1/systemone', {

    scripts/evaluate-advice.py, line 93

    with urllib.request.urlopen(req,timeout=15) as r:raw=r.read(65537)

  • Secrets

    Concern

    reads a credential or environment file.

    SECRETS_ENV_READ SECRETS_PATH_CREDENTIAL SECRETS_PATH_DOTENV

    hooks/register.js, line 32

    const value = await credentials.resolve(() => $.env.get('TYPESAFE_API_KEY'),()=>savedCredential($))

    hooks/register.js, line 145

    const configuredModel = (await $.env.get('TYPESAFE_MODEL'))?.trim() || 'jev-latest'

    docs/validation.md, line 17

    Two isolated tests of the host's generic sensitive configuration found a plaintext `.credentials.json` fallback under restricted Keychain access and an empty-value update that did

    Show more

    hooks/register.js, line 216

    $.env.get('ANTHROPIC_DEFAULT_HAIKU_MODEL'), $.env.get('ANTHROPIC_DEFAULT_SONNET_MODEL'),

    hooks/register.js, line 217

    $.env.get('ANTHROPIC_DEFAULT_OPUS_MODEL'), $.env.get('CLAUDE_CODE_USE_BEDROCK'),

    hooks/register.js, line 218

    $.env.get('CLAUDE_CODE_USE_VERTEX'), $.env.get('CLAUDE_CODE_USE_FOUNDRY'), $.env.get('ANTHROPIC_BASE_URL'),

    scripts/benchmark.py, line 405

    if not args.offline and not os.environ.get('TYPESAFE_API_KEY'):parser.error('Run from the shell holding TYPESAFE_API_KEY and Claude authentication.')

    scripts/evaluate-advice.py, line 78

    key=os.environ.get('TYPESAFE_API_KEY','').strip()

    scripts/keychain.py, line 127

    value = os.environ.get('TYPESAFE_API_KEY')

    scripts/live-eval.py, line 160

    if not args.offline and not args.planning_only and not os.environ.get('TYPESAFE_API_KEY'):

    .gitignore, line 7

    .env

  • 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 adbd08264f71. requests shell access. No manifest field names shell or command execution. can reach api.typesafe.ai. The description does not name that host. 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: adbd08264f71fd2cd7d568f5a6632b5dd3979bb4

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