SKILLEMALL.ai
GitHub ↗ RU Sign in

FC alicloud_cli

阿里云 CLI 中文文档镜像检索与命令辅助：先走章节索引，再下钻正文页面，给出命令前必须有本地文档证据。

agentscope-ai/CoPaw Agent Skills author: agentscope-ai Apache-2.0 43 files body ≈ 610 tokens Open the sourcegithub.com↗ analyzed 2 d ago

阿里云 CLI 中文文档镜像检索与命令辅助：先走章节索引，再下钻正文页面，给出命令前必须有本地文档证据。

As a process C 53/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

IntegrationSoftware developmenttype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
F
44/100
safety, quality, tests
Safety 60%
28
Quality 40%
68
Run on models
none yet
Process rating
C
53/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Obfuscation medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The files contain invisible characters, encoded commands or comments hidden from readers but visible to the model. What you read differs from what the agent sees.

For the author

Remove invisible characters (they usually sneak in through copy-paste) and encoded strings: no catalog will pass them. Instructions for the model must be readable by a human too.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 16

✓ No critical or high findings

Medium and low: 16
  • medium Obfuscation obf-base64-blob md_mirror/zh/cli/best-practices/use-alibaba-cloud-cli-to-migrate-ecs-instances-across-regions.md:16
    Long base64-looking blob
    ![image](https://help-static-aliyun-doc.aliyuncs.com/assets/img/zh-CN/5946382571/CAEQ…svg)
  • medium Dangerous commands cmd-privilege md_mirror/zh/cli/installation-guide/install-cli-on-linux.md:72
    Privilege escalation / world-writable permissions
    sudo mv ./aliyun /usr/local/bin/
  • medium Dangerous commands cmd-privilege md_mirror/zh/cli/installation-guide/install-cli-on-macos.md:99
    Privilege escalation / world-writable permissions
    sudo mv ./aliyun /usr/local/bin
  • medium Dangerous commands cmd-execpolicy-bypass md_mirror/zh/cli/installation-guide/install-cli-on-windows.md:155
    Runs PowerShell with execution policy bypassed
    powershell.exe -ExecutionPolicy Bypass -File C:\Example\Inst…ps1
  • medium Dangerous commands cmd-execpolicy-bypass md_mirror/zh/cli/installation-guide/install-cli-on-windows.md:162
    Runs PowerShell with execution policy bypassed
    powershell.exe -ExecutionPolicy Bypass -File C:\Example\Inst…ps1 -Version 3.0.277 -InstallDir "C:\ExampleDir\AliyunCLI"
  • medium Dangerous commands cmd-execpolicy-bypass md_mirror/zh/cli/installation-guide/install-cli-on-windows.md:169
    Runs PowerShell with execution policy bypassed
    powershell.exe -ExecutionPolicy Bypass -File C:\Example\Inst…ps1 -Help
  • medium Dangerous commands cmd-privilege md_mirror/zh/cli/installation-guide/uninstall-cli.md:32
    Privilege escalation / world-writable permissions
    sudo sh -c "which aliyun | xargs -r rm -v"
  • medium Dangerous commands cmd-execpolicy-bypass md_mirror/zh/cli/installation-guide/uninstall-cli.md:273
    Runs PowerShell with execution policy bypassed
    powershell.exe -ExecutionPolicy Bypass -File <script_path>
  • medium Dangerous commands cmd-execpolicy-bypass md_mirror/zh/cli/installation-guide/uninstall-cli.md:276
    Runs PowerShell with execution policy bypassed
    powershell.exe -ExecutionPolicy Bypass -File <script_path> -Clean
  • medium Dangerous commands cmd-execpolicy-bypass md_mirror/zh/cli/installation-guide/uninstall-cli.md:279
    Runs PowerShell with execution policy bypassed
    powershell.exe -ExecutionPolicy Bypass -File <script_path> -Help
  • medium Dangerous commands cmd-execpolicy-bypass md_mirror/zh/cli/installation-guide/update-cli.md:243
    Runs PowerShell with execution policy bypassed
    powershell.exe -ExecutionPolicy Bypass -File <script_path> [-InstallDir <install_path>]
  • medium Dangerous commands cmd-shell-rc md_mirror/zh/cli/use-cli/managing-and-using-cli-plugins.md:258
    Writes to a shell startup file
    echo 'export ALIBABA_CLOUD_ESS_API_VERSION=2022-02-22' >> ~/.bashrc
  • medium Dangerous commands cmd-shell-rc md_mirror/zh/cli/use-cli/managing-and-using-cli-plugins.md:309
    Writes to a shell startup file
    echo 'export ALIBABA_CLOUD_CLI_PLUGIN_AUTO_INSTALL=true' >> ~/.bashrc
  • medium Dangerous commands cmd-shell-rc md_mirror/zh/cli/use-cli/managing-and-using-cli-plugins.md:327
    Writes to a shell startup file
    echo 'export ALIBABA_CLOUD_CLI_PLUGIN_AUTO_INSTALL_ENABLE_PRE=true' >> ~/.bashrc
  • low Dangerous commands cmd-privilege md_mirror/zh/cli/common-tools/use-the-vim-editor.md:160
    Privilege escalation / world-writable permissions (quoted — discussed, not commanded)
    * 备份文件：在执行大范围替换操作前，建议备份文件或及时使用撤销功能（`u`）以防误操作。备份命令可参考`sudo cp /etc/text.txt /etc/text.txt.bak`。
    quoted
  • low Dangerous commands cmd-privilege md_mirror/zh/cli/common-tools/use-the-vim-editor.md:399
    Privilege escalation / world-writable permissions (quoted — discussed, not commanded)
    * 解决方案2：使用`:w !sudo tee %`以管理员权限保存当前文件。如果需要变更配置文件的权限和归属，可进一步使用`sudo chown`或`sudo chmod`等命令。
    quoted

Files scanned: 43. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning name-format name should be kebab-case (lowercase letters, digits, hyphens)
  • warning description-no-when description does not say WHEN to use the skill (no "use when")

Process rating: all ten parameters 53/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 100Tools and files. No external tools needed
  • 100Steps. 36 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 610 tokens
  • 100Running it twice. No mutating operations
  • low The response is described with custom markup (9 tags): a typed call is more reliable

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Description length 52: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +4Structure: 12 headings
  • +3Step-by-step instructions: 36 items
  • +4Has examples (1 code blocks)
  • +4Reference files are cited in the instructions (3 of 3)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 68.