Grades are a hygiene check, not a security guarantee.

Claude Code, Skill

Ai Film Director Workbench

这是一套给 AI 电影、AI 短片和连续剧集使用的双 Skill 工具箱。你可以把它理解成两位协作助手:

Compatibility: Not stated.

Grade C

One Medium finding. Read the report before installing.

Graded by PlugVetRubric v2

Not a guarantee. A hygiene check of the source at the commit shown, not a security audit.

PERMISSION_SHELL_UNDECLARED

Why this grade

  • PERMISSION_SHELL_UNDECLARED Medium

    Runs shell commands that the manifest or description does not mention.

    skills/ai-film-production-system/scripts/quick_validate.py, line 50 subprocess.run([sys.executable, str(SCRIPT_DIR / "init_film_project.py"), str(root)], check=True, capture_output=True, text=True)

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

    skills/ai-film-production-system/scripts/quick_validate.py, line 50

    subprocess.run([sys.executable, str(SCRIPT_DIR / "init_film_project.py"), str(root)], check=True, capture_output=True, text=True)

    skills/ai-film-production-system/scripts/quick_validate.py, line 54

    unjustified = subprocess.run([

    skills/ai-film-production-system/scripts/quick_validate.py, line 75

    subprocess.run([

    Show more

    skills/ai-film-production-system/scripts/validate_preflight.py, line 25

    proc = subprocess.run([sys.executable, str(validator), str(spec_path), "--json"], capture_output=True, text=True, encoding="utf-8", errors="replace", env=env)

    skills/ai-film-production-system/scripts/validate_preflight.py, line 37

    proc = subprocess.run([sys.executable, str(linter), "--spec",

    skills/ai-film-production-system/scripts/validate_project.py, line 48

    layer_proc = subprocess.run([sys.executable, str(SCRIPT_DIR / "validate_project_layers.py"), str(root), "--json"], capture_output=True, text=True, encoding="utf-8")

    skills/ai-video-prompt-generator/scripts/creative_behavior_validate.py, line 21

    proc = subprocess.run(args, capture_output=True, text=True, encoding="utf-8", errors="replace")

    skills/ai-video-prompt-generator/scripts/quick_validate.py, line 22

    proc = subprocess.run(args, capture_output=True, text=True, encoding="utf-8", errors="replace")

  • 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

    skills/ai-video-prompt-generator/scripts/generate_motion_prompt.py, line 79

    parser.add_argument("--env-file", default="", help="Optional KEY=VALUE env file, e.g. a Volcengine Coding Plan .env.")

    skills/ai-video-prompt-generator/scripts/generate_prompt.py, line 88

    api_key = os.environ.get(resolved_api_key_env) or os.environ.get("OPENAI_API_KEY", "")

    skills/ai-video-prompt-generator/scripts/generate_prompt.py, line 1223

    parser.add_argument("--env-file", default="", help="Optional KEY=VALUE env file, e.g. a Volcengine Coding Plan .env.")

    Show more

    skills/ai-video-prompt-generator/scripts/generate_storyboard_prompt.py, line 49

    parser.add_argument("--env-file", default="", help="Optional KEY=VALUE env file, e.g. a Volcengine Coding Plan .env.")

    .gitignore, line 4

    Thumbs.db

    .gitignore, line 5

    .env

    .gitignore, line 7

    !.env.example

  • 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.

    OBFUSCATION_FILE_OVER_READ_CAP

    sources/neowow-wanwusheng/canvas-prompt-graph.json, line 1

    {

    sources/neowow-wanwusheng/image-prompts.md, line 1

    # 万物生|图像提示词逐条源册

    sources/neowow-wanwusheng/video-prompts.md, line 1

    # 万物生|视频提示词逐条源册

  • 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 ff4791412231. 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.

Date and source

Date checked:

View source

github.com

Commit graded: ff4791412231b95550db456b58659c4b17dbc6a4

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