SKILLEMALL.ai
GitHub ↗ RU Sign in

FF macos-desktop-control

macOS 桌面控制工具。截屏、进程管理、系统信息、剪贴板、应用控制。macOS desktop control via native tools (screencapture, ps, AppleScript). 仅支持 macOS。

Not recommendedcritical or high security findings · low grade F
ClawHub Agent Skills author: Asa-Zhang v1.5.3 MIT-0 60 files · 20 scripts body ≈ 935 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process F 31/100 · Will not run — References files that are not bundled: references/applescript_cheatsheet.md

ProcedureInfrastructuretype and topics are labelled automatically from the skill text
Runs in: OpenClaw 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) Goose OpenCode
JSON
Technical rating
F
24/100
safety, quality, tests
Safety 60%
0
Quality 40%
61
Run on models
none yet
Process rating
F
31/100
Will not run
References files that are not bundled: references/applescript_cheatsheet.md
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
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. The text references files that are not there: add them or drop the references.
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 · 31

  • high Dangerous commands cmd-persistence scripts/scheduled_task.sh:56
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    (crontab -l 2>/dev/null | grep -v "mdc-task-" || true; echo "$cron_entry") | crontab -
  • high Dangerous commands cmd-persistence scripts/scheduled_task.sh:68
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    local tasks=$(crontab -l 2>/dev/null | grep "mdc-task-" || true)
  • high Dangerous commands cmd-persistence scripts/scheduled_task.sh:101
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    (crontab -l 2>/dev/null | grep -v "mdc-task-$task_id" || true) | crontab -
  • high Dangerous commands cmd-persistence scripts/scheduled_task.sh:117
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    local task=$(crontab -l 2>/dev/null | grep "mdc-task-$task_id" || true)
  • high Dangerous commands cmd-persistence scripts/scheduled_task.sh:135
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    (crontab -l 2>/dev/null | grep -v "mdc-task-" || true) | crontab -
  • high Dangerous commands cmd-persistence scripts/setup_cron.sh:27
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    existing_cron=$(crontab -l 2>/dev/null | grep "clawhub_sync.py" || true)
  • high Dangerous commands cmd-persistence scripts/setup_cron.sh:50
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    current_crontab=$(crontab -l 2>/dev/null || echo "")
  • high Dangerous commands cmd-persistence scripts/setup_cron.sh:59
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    echo "$new_crontab" | crontab -
Medium and low: 23
  • medium Dangerous commands cmd-shell-rc references/troubleshooting.md:91
    Writes to a shell startup file
    echo 'export LANG=zh_CN.UTF-8' >> ~/.zshrc
  • medium Dangerous commands cmd-shell-rc references/troubleshooting.md:92
    Writes to a shell startup file
    echo 'export LC_ALL=zh_CN.UTF-8' >> ~/.zshrc
  • medium Dangerous commands cmd-eval-dynamic scripts/control_memory.py:275
    Dynamic code execution from decoded/untrusted input
    os.system(f"python3 {sync_script}")
  • medium Dangerous commands cmd-persistence scripts/setup_cron.sh:41
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (detector / deny-list definition)
    crontab -l 2>/dev/null | grep -v "clawhub_sync.py" | crontab -
    detector
  • medium Dangerous commands cmd-shell-rc SKILL.md:194
    Writes to a shell startup file
    echo 'alias mdc="cd ~/.openclaw/workspace/skills/macos-desktop-control && bash"' >> ~/.zshrc
  • low Dangerous commands cmd-cron-mention API_SETUP_GUIDE.md:189
    Mentions editing / listing crontab
    crontab -e
  • low Dangerous commands cmd-cron-mention API_SETUP_GUIDE.md:197
    Mentions editing / listing crontab
    crontab -l | grep clawhub
  • low Dangerous commands cmd-cron-mention CHANGELOG_v1.5.0.md:274
    Mentions editing / listing crontab
    crontab -e
  • low Dangerous commands cmd-privilege scripts/reset_permissions.sh:3
    Privilege escalation / world-writable permissions (code comment)
    # 用法：sudo bash reset_permissions.sh
    comment
  • low Dangerous commands cmd-privilege scripts/reset_permissions.sh:13
    Privilege escalation / world-writable permissions (string literal in code, not executed)
    echo "   sudo bash $0"
    code literal
  • low Dangerous commands cmd-cron-mention scripts/scheduled_task.sh:56
    Mentions editing / listing crontab
    (crontab -l 2>/dev/null | grep -v "mdc-task-" || true; echo "$cron_entry") | crontab -
  • low Dangerous commands cmd-cron-mention scripts/scheduled_task.sh:68
    Mentions editing / listing crontab
    local tasks=$(crontab -l 2>/dev/null | grep "mdc-task-" || true)
  • low Dangerous commands cmd-cron-mention scripts/scheduled_task.sh:101
    Mentions editing / listing crontab
    (crontab -l 2>/dev/null | grep -v "mdc-task-$task_id" || true) | crontab -
  • low Dangerous commands cmd-cron-mention scripts/scheduled_task.sh:117
    Mentions editing / listing crontab
    local task=$(crontab -l 2>/dev/null | grep "mdc-task-$task_id" || true)
  • low Dangerous commands cmd-cron-mention scripts/scheduled_task.sh:135
    Mentions editing / listing crontab
    (crontab -l 2>/dev/null | grep -v "mdc-task-" || true) | crontab -
  • low Dangerous commands cmd-cron-mention scripts/setup_cron.sh:27
    Mentions editing / listing crontab
    existing_cron=$(crontab -l 2>/dev/null | grep "clawhub_sync.py" || true)
  • low Dangerous commands cmd-cron-mention scripts/setup_cron.sh:41
    Mentions editing / listing crontab
    crontab -l 2>/dev/null | grep -v "clawhub_sync.py" | crontab -
  • low Dangerous commands cmd-cron-mention scripts/setup_cron.sh:50
    Mentions editing / listing crontab
    current_crontab=$(crontab -l 2>/dev/null || echo "")
  • low Dangerous commands cmd-cron-mention scripts/setup_cron.sh:70
    Mentions editing / listing crontab (string literal in code, not executed)
    echo "   crontab -l"
    code literal
  • low Dangerous commands cmd-cron-mention scripts/setup_cron.sh:76
    Mentions editing / listing crontab (detector / deny-list definition; string literal in code, not executed)
    echo "   crontab -l | grep -v clawhub_sync.py | crontab -"
    detectorcode literal
  • low Dangerous commands cmd-cron-mention SYNC_TEST_REPORT.md:110
    Mentions editing / listing crontab (test fixture / example file)
    crontab -l | grep clawhub
    fixture
  • low Dangerous commands cmd-cron-mention SYNC_TEST_REPORT.md:292
    Mentions editing / listing crontab (test fixture / example file)
    crontab -e
    fixture
  • low Dangerous commands cmd-cron-mention SYNC_TEST_REPORT.md:300
    Mentions editing / listing crontab (test fixture / example file)
    crontab -l | grep clawhub
    fixture

Files scanned: 60. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning missing-ref reference to a missing file: references/applescript_cheatsheet.md
  • note frontmatter-key unknown frontmatter key "platform"

Process rating: all ten parameters 31/100

Will not run. References files that are not bundled: references/applescript_cheatsheet.md
  • 0Tools and files. 1 referenced file(s) missing: references/applescript_cheatsheet.md
  • 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 (macos-desktop-control) differs from the folder (macos-desktop-control-zhang)
  • 100Steps. 8 steps
  • 100Execution cost. Instruction body is 935 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

  • +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 118: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -212 emoji in the instructions: noise for the model
  • -322 of 30 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +4Structure: 24 headings
  • +3Step-by-step instructions: 8 items
  • +4Has examples (17 code blocks)
  • +4Reference files are cited in the instructions (2 of 2)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 61.

External checks

ClawHub: suspicious
This macOS control skill does useful local automation, but it also includes under-disclosed cloud sync, cron scheduling, and raw command execution paths that deserve manual review before installation.
LLM: suspicious (high) · VirusTotal: · 29 May 2026