Grades are a hygiene check, not a security guarantee.

Codex, Plugin

Codex Reasoning Assistant

This plugin first reads the active configuration and assesses whether it fits the task.

Compatibility: Not stated.

Grade B

Minor issues only, no Medium or High. Worth a quick look at the findings below 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 62221bcf5a95, unchanged since the check below.

PERMISSION_SHELL_DECLARED SECRETS_ENV_READ

Why this grade

  • PERMISSION_SHELL_DECLARED Note

    Runs shell commands, and the manifest or description says so.

    plugins/codex-reasoning-assistant/scripts/measure_performance.py, line 199 subprocess.run(

  • SECRETS_ENV_READ Note

    Reads an environment variable whose name contains KEY, SECRET, TOKEN, PASSWORD or CREDENTIAL.

    plugins/codex-reasoning-assistant/hooks/reasoning_effort_context.py, line 963 configured = os.environ.get("REASONING_ASSISTANT_STATE_KEY")

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

    plugins/codex-reasoning-assistant/scripts/measure_performance.py, line 199

    subprocess.run(

    plugins/codex-reasoning-assistant/scripts/verify.py, line 266

    result = subprocess.run(

    plugins/codex-reasoning-assistant/scripts/verify.py, line 372

    result = subprocess.run(

    Show more

    plugins/codex-reasoning-assistant/scripts/verify.py, line 398

    health = subprocess.run(

    plugins/codex-reasoning-assistant/scripts/verify.py, line 410

    invalid = subprocess.run(

    plugins/codex-reasoning-assistant/scripts/verify.py, line 452

    mcp_result = subprocess.run(

    plugins/codex-reasoning-assistant/scripts/verify.py, line 484

    subprocess.run(

    plugins/codex-reasoning-assistant/scripts/verify_four_layers.py, line 80

    result = subprocess.run(

  • Install and update

    Pass

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

  • Network

    Pass

    No network call found.

  • Secrets

    Note

    reads an environment variable.

    SECRETS_ENV_READ

    plugins/codex-reasoning-assistant/hooks/reasoning_effort_context.py, line 963

    configured = os.environ.get("REASONING_ASSISTANT_STATE_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 62221bcf5a95. requests shell access. The manifest names this permission. reads an environment variable.

Date and source

Date checked:

View source

github.com

Commit graded: 62221bcf5a95d86dae6ac2dbbff3aaeee3842486

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