Grades are a hygiene check, not a security guarantee.

Claude Code, Skill

Ai Agent Handbook

Ai Agent Handbook, a skill listed in the PlugVet directory.

Compatibility: Not stated.

Grade C

One Medium finding. Read the findings 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 4354b14fcc29, unchanged since the check below.

INSTALL_REMOTE_SCRIPT

Why this grade

  • INSTALL_REMOTE_SCRIPT Medium

    Fetches a script from the network and runs it (a pipe to a shell, or an install hook with a URL).

    chapters/12-ollama.md, line 38 curl -fsSL https://ollama.com/install.sh | sh

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.

If you think this grade is wrong, email [email protected] with the entry link and your evidence. We aim to acknowledge within two working days and decide within seven. If we confirm an error, we aim to correct it within 24 hours of confirming it. These are aims, not guarantees.

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

    build_backend.py, line 41

    shutil.rmtree(dst_chapters)

    build_backend.py, line 49

    shutil.rmtree(dst_data)

    scripts/build_cli.py, line 32

    result = subprocess.run(

    Show more

    scripts/build_docs.py, line 44

    shutil.rmtree(STAGE)

    scripts/build_pdf.py, line 146

    subprocess.run(cmd, capture_output=True, timeout=300)

    chapters/26-agent-skills.md, line 358

    result = subprocess.run(cmd, capture_output=True, text=True)

  • Install and update

    Serious

    install fetches a script from the network.

    INSTALL_REMOTE_SCRIPT

    chapters/12-ollama.md, line 38

    curl -fsSL https://ollama.com/install.sh | sh

    requirements.txt, line 8

    openai>=1.30.0 # OpenAI / 国产模型通用客户端

  • Network

    Concern

    can reach a host that is not written as a fixed address. can reach api.weather.example. The description does not name that host.

    NETWORK_NO_FIXED_HOST NETWORK_UNNAMED_HOST

    scripts/freshness_check.py, line 47

    resp = requests.get(url, headers=headers, timeout=15)

    scripts/refresh_stars.py, line 48

    resp = requests.get(url, headers=headers, timeout=15)

    scripts/refresh_stars.py, line 56

    rel_resp = requests.get(release_url, headers=headers, timeout=15)

    Show more

    chapters/07-dify.md, line 189

    response = requests.post(

    chapters/07-dify.md, line 209

    response = requests.post(

    chapters/11-mcp.md, line 357

    const resp = await fetch(`https://api.weather.example/${city}`);

    chapters/11-mcp.md, line 367

    async fetch(request, env) {

    chapters/12-ollama.md, line 74

    response = requests.post(

  • Secrets

    Concern

    reads a credential or environment file.

    SECRETS_ENV_READ SECRETS_PATH_DOTENV

    examples/01-react-agent/main.py, line 29

    api_key = os.getenv("OPENAI_API_KEY")

    examples/04-autogen-chat/main.py, line 14

    "api_key": os.getenv("OPENAI_API_KEY")

    examples/07-final-project/main.py, line 160

    system = ResearchSystem(api_key=os.getenv("OPENAI_API_KEY"))

    Show more

    examples/11-mini-harness/main.py, line 21

    cp .env.example .env # 填入 OPENAI_API_KEY / DEEPSEEK_API_KEY

    examples/11-mini-harness/main.py, line 42

    try: # 加载 .env（可选依赖，缺了不影响离线演示）

    examples/11-mini-harness/main.py, line 45

    load_dotenv(Path(__file__).parent / ".env")

    examples/11-mini-harness/main.py, line 354

    api_key = os.getenv("OPENAI_API_KEY") or os.getenv("DEEPSEEK_API_KEY")

    examples/11-mini-harness/main.py, line 667

    os.getenv("OPENAI_API_KEY") or os.getenv("DEEPSEEK_API_KEY")

    scripts/freshness_check.py, line 42

    token = os.environ.get("GITHUB_TOKEN")

    scripts/refresh_stars.py, line 44

    token = os.environ.get("GITHUB_TOKEN")

    src/agent_handbook/cli.py, line 95

    print(" cp .env.example .env # 填上模型地址与 Key")

    src/agent_handbook/scaffold.py, line 14

    3. 把 .env.example 复制为 .env 并填写

    src/agent_handbook/scaffold.py, line 24

    TOKEN_BUDGET = int(os.getenv("TOKEN_BUDGET", "60000"))

    src/agent_handbook/scaffold.py, line 154

    return "[离线模式] 未配置模型。复制 .env.example 为 .env 并填写后可真实调用。"

    src/agent_handbook/scaffold.py, line 228

    ENV_EXAMPLE = """# 复制为 .env 后填写（.env 已在 .gitignore 中）

    src/agent_handbook/scaffold.py, line 246

    cp .env.example .env # 填模型地址与 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.

Get the full report on this tool, £49

Note

Hygiene check of commit 4354b14fcc29. can delete files. install fetches a script from the network. can reach a host that is not written as a fixed address. can reach api.weather.example. The description does not name that host. reads a credential or environment file.

Date and source

Date checked:

View source

github.com

Commit graded: 4354b14fcc29d3199723b59f7fd507e9052cdf69

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