Grades are a hygiene check, not a security guarantee.

Codex, Plugin

Arcgentic

Mechanical plan/dev/self-audit/external-audit gates for AI coding agents, with a configurable role-routing topology engine, an MCP-UI live status panel, and native-tooling Claude Code V2 dispatch.

Compatibility: Portable across standard formats.

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 853995505285, unchanged since the check below.

SECRETS_PATH_DOTENV PERMISSION_SHELL_DECLARED

Why this grade

  • SECRETS_PATH_DOTENV Low

    Mentions a .env file.

    PRIVACY.md, line 28 Arcgentic does not read credential stores, keychains, password managers, browser profiles, OAuth tokens, API keys, `.env` files, or other secrets as part of its core workflow.

  • PERMISSION_SHELL_DECLARED Note

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

    toolkit/src/arcgentic/audit_check.py, line 207 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

    Note

    requests shell access. The manifest names this permission.

    PERMISSION_SHELL_DECLARED

    toolkit/src/arcgentic/audit_check.py, line 207

    result = subprocess.run(

    toolkit/src/arcgentic/adapters/_local_env.py, line 54

    result = subprocess.run(

    toolkit/src/arcgentic/adapters/_local_env.py, line 78

    result = subprocess.run(

    Show more

    toolkit/src/arcgentic/adapters/claude_code.py, line 14

    - `shell`: subprocess.run with shell=True; timeout enforced.

    toolkit/src/arcgentic/adapters/claude_code.py, line 81

    result = subprocess.run(

    toolkit/src/arcgentic/adapters/claude_code.py, line 118

    result = subprocess.run(

    toolkit/src/arcgentic/adapters/claude_code.py, line 158

    result = subprocess.run(

    toolkit/src/arcgentic/adapters/claude_code.py, line 206

    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

    Concern

    reads a credential or environment file.

    SECRETS_PATH_DOTENV

    PRIVACY.md, line 28

    Arcgentic does not read credential stores, keychains, password managers, browser profiles, OAuth tokens, API keys, `.env` files, or other secrets as part of its core workflow.

    docs/distribution/plugin-submission-packet.md, line 84

    | Secrets | No secret reads. No `.env`, keychain, credential store, or token exfiltration path is part of the plugin. |

  • 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 853995505285. 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: 8539955052859f315436b961465341c7bc2b3c20

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