BD c-disk-cleanup-pro
面向电脑小白的 Windows C 盘清理助手（经真机实战验证）。两种模式：①开荒保洁——C盘已爆满时，先只读体检、用大白话讲清每类文件是什么/删了有啥影响，等用户逐条点头才动手，且一律只搬不删、可恢复；②日常保洁——记住你的清理习惯，定期自动体检或你随时喊一声，只清安全项。绝不自行删除任何文件，任何清理动作前必须取得用户明确同意。实战已验证：微信等聊天数据走官方"更改存储位置"迁移、可重建缓存只搬 Cache/Temp 子目录、软件主程序目录绝不碰、搬前检测进程锁防"半搬走"。触发词："C盘满了""C盘爆红""清理C盘""C盘瘦身""腾空间""定期清理C盘""电脑卡"。
面向电脑小白的 Windows C…
As a process D 49/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
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.
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
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 · 8
✓ No critical or high findings
Medium and low: 8
-
medium Dangerous commands
cmd-execpolicy-bypassreferences/workflow.md:36Runs PowerShell with execution policy bypassedpowershell -ExecutionPolicy Bypass -File scripts/safe…ps1 `
-
low Dangerous commands
cmd-execpolicy-bypassreferences/troubleshooting.md:59Runs PowerShell with execution policy bypassed (quoted — discussed, not commanded)- 写脚本与运行分开：先用 `Write`/编辑器把 .ps1 写到**工作区或 D 盘**（非 C 盘系统目录），再用 `powershell -ExecutionPolicy Bypass -File 脚本路径` 运行。
quoted -
low Dangerous commands
cmd-execpolicy-bypassscripts/find_backup_drive.ps1:2Runs PowerShell with execution policy bypassed (code comment)# 用法: powershell -ExecutionPolicy Bypass -File find…ps1
comment -
low Dangerous commands
cmd-execpolicy-bypassscripts/safe_ops.ps1:11Runs PowerShell with execution policy bypassed (code comment)# powershell -ExecutionPolicy Bypass -File safe…ps1 -Action MoveToBackup -Path "C:\Users\me\AppData\Local\Temp" -BackupDrive D
comment -
low Dangerous commands
cmd-execpolicy-bypassscripts/safe_ops.ps1:13Runs PowerShell with execution policy bypassed (code comment)# powershell -ExecutionPolicy Bypass -File safe…ps1 -Action MoveToBackup -Path "..." -BackupDrive D -Confirmed
comment -
low Dangerous commands
cmd-execpolicy-bypassscripts/safe_ops.ps1:15Runs PowerShell with execution policy bypassed (code comment)# powershell -ExecutionPolicy Bypass -File safe…ps1 -Action WindowsClean -Confirmed
comment -
low Dangerous commands
cmd-execpolicy-bypassscripts/safe_ops.ps1:17Runs PowerShell with execution policy bypassed (code comment)# powershell -ExecutionPolicy Bypass -File safe…ps1 -Action SendToRecycle -Path "..." -Confirmed
comment -
low Dangerous commands
cmd-execpolicy-bypassscripts/scan_cdrive.ps1:2Runs PowerShell with execution policy bypassed (code comment; documentation of a security skill)# 用法: powershell -ExecutionPolicy Bypass -File scan…ps1
commentsecurity skill
Files scanned: 12. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - note
frontmatter-keyunknown frontmatter key "display_name" - note
frontmatter-keyunknown frontmatter key "risk_level" - note
frontmatter-keyunknown frontmatter key "requires_consent"
Process rating: all ten parameters 49/100
- 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
- 40Consistency. Frontmatter name (c-disk-cleanup-pro) differs from the folder (c-disk-cleanup)
- 100Tools and files. No external tools needed
- 100Steps. 58 steps
- 100Execution cost. Instruction body is 1156 tokens
- 100Running it twice. No mutating operations
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 2 example trigger phrases
- +3Description length 289: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 58 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +3All 3 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.