Grades are a hygiene check, not a security guarantee.

Codex, Plugin

Codex Ai Game Studio

Codex AI game studio: 85 skills, 163 curated tools, Unity/Godot/Unreal/Blender workflows, img2threejs, reversible automation, and visual QA.

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 bebc1c7fb0bd, 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.

    parity/tools/generate_parity.py, line 343 result = subprocess.run(

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

    parity/tools/generate_parity.py, line 343

    result = subprocess.run(

    parity/tools/generate_parity.py, line 1058

    if subprocess.run(

    plugins/ai-game-studio/scripts/ags_core.py, line 163

    result = subprocess.run(

    Show more

    plugins/ai-game-studio/scripts/ags_core.py, line 346

    probe = subprocess.run(

    plugins/ai-game-studio/scripts/ags_core.py, line 375

    probe = subprocess.run(

    plugins/ai-game-studio/scripts/ags_core.py, line 404

    probe = subprocess.run([system_profiler, "SPDisplaysDataType", "-json"], capture_output=True, text=True, timeout=6, check=False, errors="replace")

    plugins/ai-game-studio/scripts/ags_core.py, line 418

    probe = subprocess.run([lspci], capture_output=True, text=True, timeout=4, check=False, errors="replace")

    plugins/ai-game-studio-automation/scripts/migrate_claude.py, line 16

    return subprocess.run([sys.executable, str(core), "migrate", "claude", *sys.argv[1:]], check=False).returncode

  • Install and update

    Pass

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

  • Network

    Pass

    No network call found.

  • Secrets

    Concern

    reads a credential or environment file.

    SECRETS_ENV_READ SECRETS_PATH_DOTENV

    plugins/ai-game-studio/scripts/ags_core.py, line 1457

    token = os.environ.get("GH_TOKEN") or os.environ.get("GITHUB_TOKEN")

    SUPPORT.md, line 7

    Before asking for help, run the read-only doctor and attach its redacted JSON output plus the validation summary. Never attach tokens, `.env` contents, private project assets, unpu

    docs/CATALOG_CONTRIBUTING.md, line 44

    List only environment-variable names such as `PROVIDER_API_KEY`; never values, examples that resemble live credentials, local `.env` contents, or headers. State whether inputs/outp

    Show more

    docs/privacy/index.md, line 40

    Do not paste API keys, tokens, private keys, `.env` contents, unreleased proprietary assets, biometric/identity data, or unconsented voice recordings into public issues, Discussion

    docs/support/index.md, line 11

    Attach a redacted `doctor` result, relevant plan ID (not secrets), operating system, Codex surface, plugin version, and exact error. Do not attach proprietary assets, tokens, `.env

  • Agent instructions

    Pass

    No instruction to ignore earlier instructions or to hide a step.

  • Obfuscation

    Note

    a file was over the read cap and was not fully read. the file cap was reached before every file was read.

    OBFUSCATION_FILE_OVER_READ_CAP OBFUSCATION_FILE_CAP_REACHED

    plugins/ai-game-studio/catalog/catalog.json, line 1

    {

    plugins/ai-game-studio-img2threejs/skills/img2threejs/agents/openai.yaml, line 1

    interface:

  • 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 bebc1c7fb0bd. requests shell access. No manifest field names shell or command execution. reads a credential or environment file. a file was over the read cap and was not fully read. the file cap was reached before every file was read.

Date and source

Date checked:

View source

github.com

Commit graded: bebc1c7fb0bded12593257333cbe096fd630aaa0

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