Grades are a hygiene check, not a security guarantee.

Codex, Plugin

Engineer Software

Evidence-driven engineering workflows for Codex and DeepSeek Harness, backed by deterministic routing and behavior evaluations.

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 aef0fd2c74fa, unchanged since the check below.

SECRETS_PATH_DOTENV PERMISSION_SHELL_DECLARED

Why this grade

  • SECRETS_PATH_DOTENV Low

    Mentions a .env file.

    .gitignore, line 8 .env

  • PERMISSION_SHELL_DECLARED Note

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

    scripts/prepare_behavior_worktrees.py, line 27 completed = subprocess.run(command, cwd=cwd, capture_output=True, text=True, check=False)

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

    scripts/prepare_behavior_worktrees.py, line 27

    completed = subprocess.run(command, cwd=cwd, capture_output=True, text=True, check=False)

    scripts/run_behavior_eval.py, line 131

    status = subprocess.run(

    scripts/run_behavior_eval.py, line 140

    diff = subprocess.run(

    Show more

    scripts/run_behavior_eval.py, line 149

    patch = subprocess.run(

    scripts/run_behavior_eval.py, line 158

    untracked = subprocess.run(

    scripts/run_behavior_eval.py, line 266

    completed = subprocess.run(

    scripts/run_routing_eval.py, line 125

    completed = subprocess.run(

  • 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_PATH_DOTENV

    .gitignore, line 7

    venv/

    .gitignore, line 8

    .env

    README.md, line 186

    - Never commit API keys, `.env` files, session logs, profile state, generated temporary assets, or

    Show more

    README.zh-CN.md, line 264

    本项目只提供指令和校验脚本，不包含 MCP server、hook、遥测、凭据存储或后台服务。宿主运行时仍可能访问用户授权的工具、代码和模型服务；请在提交前审阅生成文件，避免把 secrets、`.env`、session logs、个人数据或未经审阅的截图放入仓库。

    docs/compatibility.md, line 137

    placing them in a user-global skill directory, and never commit API keys, `.env` files, session logs,

  • 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 aef0fd2c74fa. requests shell access. The manifest names this permission. reads a credential or environment file.

Date and source

Date checked:

View source

github.com

Commit graded: aef0fd2c74fa36ad6a19e93d38404bdc8fad7943

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