Grades are a hygiene check, not a security guarantee.

Cursor, Plugin

Modellix Plugin

Agent plugin for AI image and video generation via Modellix API/CLI.

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 98d1cde09cdf, unchanged since the check below.

PERMISSION_DELETE_FILES NETWORK_UNNAMED_HOST SECRETS_PATH_DOTENV SECRETS_ENV_READ

Why this grade

  • PERMISSION_DELETE_FILES Low

    Contains a call that can delete files.

    skills/modellix-design/scripts/clean_build_artifacts.py, line 31 shutil.rmtree(cache_dir, ignore_errors=True)

  • NETWORK_UNNAMED_HOST Low

    Calls a fixed host that the description does not name.

    skills/modellix-design/references/rest-playbook.md, line 38 curl -X POST "https://api.modellix.ai/api/v1/google/nano-banana-2-lite/async" \

  • SECRETS_PATH_DOTENV Low

    Mentions a .env file.

    AGENTS.md, line 254 - Never commit credentials / `.env` / keyed profiles. Session-only credentials by default.

  • SECRETS_ENV_READ Note

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

    scripts/modellix_run_guard.py, line 42 if (os.getenv("MODELLIX_API_KEY") or "").strip():

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

    can delete files.

    PERMISSION_DELETE_FILES

    skills/modellix-design/scripts/clean_build_artifacts.py, line 31

    shutil.rmtree(cache_dir, ignore_errors=True)

    skills/modellix-design/scripts/cli_runtime.py, line 90

    run = run_command or subprocess.run

    skills/modellix-design/scripts/cli_runtime.py, line 353

    shutil.rmtree(lock_root)

    Show more

    skills/modellix-design/scripts/invoke_and_poll.py, line 133

    proc = subprocess.run(

    skills/modellix-design/scripts/invoke_and_poll.py, line 173

    proc = subprocess.run(

    skills/modellix-design/scripts/preflight.py, line 27

    proc = subprocess.run(

    .github/workflows/skill_update.yml, line 107

    result = subprocess.run(

    .github/workflows/skill_update.yml, line 116

    result = subprocess.run(

    .github/workflows/skill_update.yml, line 203

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

  • Install and update

    Pass

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

  • Network

    Concern

    can reach api.modellix.ai. The description does not name that host.

    NETWORK_UNNAMED_HOST

    skills/modellix-design/references/rest-playbook.md, line 38

    curl -X POST "https://api.modellix.ai/api/v1/google/nano-banana-2-lite/async" \

    skills/modellix-design/references/rest-playbook.md, line 65

    curl -X GET "https://api.modellix.ai/api/v1/tasks/<task_id>?wait=true&timeout=45" \

  • Secrets

    Concern

    reads a credential or environment file.

    SECRETS_ENV_READ SECRETS_PATH_DOTENV

    scripts/modellix_run_guard.py, line 42

    if (os.getenv("MODELLIX_API_KEY") or "").strip():

    skills/modellix-design/scripts/invoke_and_poll.py, line 78

    key = args.api_key or os.getenv("MODELLIX_API_KEY")

    AGENTS.md, line 254

    - Never commit credentials / `.env` / keyed profiles. Session-only credentials by default.

    Show more

    skills/modellix-design/scripts/preflight.py, line 56

    env_key_available = bool((os.getenv("MODELLIX_API_KEY") or "").strip())

    CHANGELOG.md, line 169

    - Hermes Agent skill metadata in `SKILL.md`: `metadata.hermes.tags` and `required_environment_variables` for `MODELLIX_API_KEY` (secure prompt / `~/.hermes/.env`).

    README.md, line 317

    Update: re-run `hermes skills install ...`, or `git pull` on a symlink checkout. After install, start a new session and invoke `/modellix` (or load the skill via Hermes skill tools

    README.md, line 333

    - In Hermes, prefer `~/.hermes/.env` or a session environment variable.

  • 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 98d1cde09cdf. can delete files. can reach api.modellix.ai. The description does not name that host. reads a credential or environment file.

Date and source

Date checked:

View source

github.com

Commit graded: 98d1cde09cdfad1f12fd9f1332ac177647f0e5e6

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