SKILLEMALL.ai
RU Sign in

FD winskill

Windows 服务器运维工具箱 - 磁盘分析、临时文件清理、IIS 站点管理、批量文件操作、服务状态监控、Windows Update 诊断、实时性能监控、安全审计、注册表启动项审计、磁盘健康检测、网络端口监控、事件日志诊断、已安装程序管理、用户会话监控、计划任务审计、文件共享审计、DNS网卡诊断、SSL证书过期检测、防火墙规则审计、服务崩溃恢复状态、系统文件修复、存储池管理、备份状态检查、Docker容器管理、K8s集群监控、自动化修复向导、性能基线与趋势分析、等保合规检查清单、远程多服务器管理、日志轮转、模块索引、轻量常驻监控、趋势预测、告警推送。只读分析+安全确认，绝不误删文件，完全免费离线运行。

Not recommendedcritical or high security findings · low grade F
ClawHub Hermes author: fyniujin v3.3.0 MIT-0 39 files · 1 script body ≈ 1 661 tokens Open the sourceclawhub.ai↗ analyzed 21 h ago

Windows 服务器运维工具箱 - 磁盘分析、临时文件清理、IIS 站点管理、批量文件操作、服务状态监控、Windows Update…

As a process D 48/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedureDockerKubernetesInfrastructureSecuritySoftware developmenttype and topics are labelled automatically from the skill text
Runs in: OpenClaw Hermes Agent
JSON
Technical rating
F
33/100
safety, quality, tests
Safety 60%
16
Quality 40%
58
Run on models
none yet
Process rating
D
48/100
Unfinished process
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

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Dangerous commands
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. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
  2. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  3. For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
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 · 13

  • high Dangerous commands cmd-encoded-exec references/modules/module-17-计划任务审计.md:78
    Executes a base64/encoded payload (detector / deny-list definition)
    if ($argStr -match '((?:powershell|cmd|wscript|cscript|rundll32|mshta|regsvr32).*?(?:-enc|-e\s|IEX|Invoke-Expression|DownloadString|From…ing|eval))') {
    detector
  • high Dangerous commands cmd-persistence references/modules/module-28-性能基线-&-趋势分析.md:42
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    Register-ScheduledTask -TaskName $taskName -Action $action -Trigger $trigger -Description "Winskill 性能基线采集（7 天）" -Force
  • high Dangerous commands cmd-persistence references/modules/module-31-轻量常驻监控.md:135
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    Register-ScheduledTask -TaskName $taskName -Action $action -Trigger $trigger -Settings $settings -User "SYSTEM" -RunLevel Highest -Force
Medium and low: 10
  • medium Dangerous commands cmd-persistence references/modules/module-11-注册表与启动项安全审计.md:32
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)
    "HKLM:\Software\Microsoft\Windows\CurrentVersion\Run",
    quoted
  • medium Dangerous commands cmd-persistence references/modules/module-11-注册表与启动项安全审计.md:34
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)
    "HKCU:\Software\Microsoft\Windows\CurrentVersion\Run",
    quoted
  • medium Dangerous commands cmd-persistence references/modules/module-11-注册表与启动项安全审计.md:36
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)
    "HKLM:\Software\WOW6432Node\Microsoft\Windows\CurrentVersion\Run"
    quoted
  • medium Dangerous commands cmd-persistence references/modules/module-28-性能基线-&-趋势分析.md:304
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation table row)
    | `Register-ScheduledTask 拒绝访问` | 需要管理员权限 | 以管理员身份运行 PowerShell |
    table
  • medium Dangerous commands cmd-persistence references/modules/module-31-轻量常驻监控.md:173
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation table row)
    | `Register-ScheduledTask 拒绝访问` | 需要管理员权限 | 以管理员身份运行 PowerShell |
    table
  • low Secrets in code secret-high-entropy-token references/modules/module-28-性能基线-&-趋势分析.md:39
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    -Command "& {`$csv='$csvFile'; `$cpu=(Get-CimInstance Win3…sor).LoadPercentage; `$mem=(Get-CimInstance Win3…tem); `$memPct=[math]::Round(($mem.TotalVisibleMemorySize - `$mem.FreePh
    detector
  • low Secrets in code secret-high-entropy-token references/modules/module-28-性能基线-&-趋势分析.md:221
    High-entropy token-like string (may be an id, hash or a credential)
    $disk = Get-CimInstance Win3…isk | Where-Object Name -eq "_Total"
  • low Secrets in code secret-high-entropy-token references/modules/module-28-性能基线-&-趋势分析.md:223
    High-entropy token-like string (may be an id, hash or a credential)
    $net = Get-CimInstance Win3…ace | Where-Object Name -notlike '*Loopback*'
  • low Dangerous commands cmd-execpolicy-bypass references/modules/module-31-轻量常驻监控.md:131
    Runs PowerShell with execution policy bypassed (detector / deny-list definition)
    $action = New-ScheduledTaskAction -Execute "powershell.exe" -Argument "-NoProfile -ExecutionPolicy Bypass -File `"$samplerPath`""
    detector
  • low Dangerous commands cmd-execpolicy-bypass references/modules/module-31-轻量常驻监控.md:174
    Runs PowerShell with execution policy bypassed (documentation table row; security demo / example)
    | `在此系统上禁止运行脚本` | 执行策略限制 | 安装脚本已用 `-ExecutionPolicy Bypass`，若仍报错先 `Set-ExecutionPolicy RemoteSigned -Scope CurrentUser` |
    tabledemo

Files scanned: 39. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-long-hermes description is 306 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period)
  • warning description-no-when neither description nor a "## When to Use" section says when to use the skill
  • note frontmatter-key unknown frontmatter key "slug"
  • note frontmatter-key unknown frontmatter key "displayName"
  • note frontmatter-key unknown frontmatter key "description_zh"
  • note frontmatter-key unknown frontmatter key "requires_api_key"

Process rating: all ten parameters 48/100

  • 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
  • 20When it triggers. No condition that starts the skill
  • 60Tools and files. Uses tools (bash) that frontmatter does not declare
  • 100Steps. 5 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 1661 tokens
  • 100Running it twice. No mutating operations
  • 100Progress reporting. Reports progress

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)
  • +3Output format is not stated: the model decides each time
  • -212 emoji in the instructions: noise for the model
  • -31 of 1 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +3Description length 306: enough signal without eating the budget
  • +4Structure: 17 headings
  • +3Step-by-step instructions: 5 items
  • +4Has examples (3 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 58.

External checks

ClawHub: suspicious
This is a real Windows server admin toolbox, but review is needed because some modules can persistently change systems, store credentials, and run commands across servers despite read-only framing.
LLM: suspicious (high) · 11 Sept 2026