SKILLEMALL.ai
GitHub ↗ RU Sign in

BC desktop-guardian

macOS GUI automation and desktop control for OpenClaw, powered by Hammerspoon. Gives your agent full access to interact with the Mac desktop — query windows, manage apps, close browser tabs, click dialog buttons, dismiss popups, and send keypresses. Includes an always-on desktop guardian that actively monitors for system dialogs, permission prompts, error popups, and unauthorized apps, taking action automatically or alerting you when human input is needed. Use when: (1) your agent needs to interact with the macOS GUI, (2) monitoring and responding to desktop popups/dialogs/alerts, (3) managing open apps, browser windows, and tabs, (4) enforcing desktop cleanliness policies, (5) any macOS Accessibility automation from OpenClaw.

Not recommendedcritical or high security findings
modbender/skill-library-mcp Agent Skills author: modbender MIT 10 files · 3 scripts body ≈ 998 tokens Open the sourcegithub.com↗ analyzed 2 d ago

macOS GUI automation and desktop control for OpenClaw, powered by Hammerspoon.

As a process C 56/100 · Has gaps — weak spots: result and completion, when it triggers, running it twice

IntegrationInfrastructureAI and agentstype 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
B
75/100
safety, quality, tests
Safety 60%
74
Quality 40%
77
Run on models
none yet
Process rating
C
56/100
Has gaps
Result and completion w 14
0
When it triggers w 12
20
Running it twice w 4
30
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.
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 · 5

  • high Dangerous commands cmd-persistence scripts/install.sh:212
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl bootstrap "gui/$(id -u)" "$LAUNCH_AGENT_PLIST"
Medium and low: 4
  • medium Dangerous commands cmd-persistence scripts/install.sh:12
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
    OLD_AGENT_PLIST="$HOME/Library/LaunchAgents/${OLD_AGENT_LABEL}.plist"
    code literal
  • low Dangerous commands cmd-persistence scripts/install.sh:10
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (detector / deny-list definition; string literal in code, not executed)
    LAUNCH_AGENT_PLIST="$HOME/Library/LaunchAgents/${LAUNCH_AGENT_LABEL}.plist"
    detectorcode literal
  • low Dangerous commands cmd-persistence scripts/uninstall.sh:6
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (detector / deny-list definition; string literal in code, not executed)
    LAUNCH_AGENT_PLIST="$HOME/Library/LaunchAgents/${LAUNCH_AGENT_LABEL}.plist"
    detectorcode literal

A further 1 matches are quotations in this security skill's documentation and are not counted as findings.

Files scanned: 9. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

✓ No remarks against the Agent Skills spec

Process rating: all ten parameters 56/100

  • 0Result and completion. Does not say what the result is
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 6 mutating operations with no state check
  • 50Failures and branches. 0 branches, has a failure section
  • 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 85Steps. 33 steps, 3 vague phrases
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 998 tokens
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 10 top-level sections: this looks like several domains in one skill

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
  • -43 reference files, but SKILL.md never points to them: the model will not open them
  • -31 of 4 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +3Description length 736: enough signal without eating the budget
  • +4Structure: 13 headings
  • +3Step-by-step instructions: 33 items
  • +4Has examples (6 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.