SKILLEMALL.ai
GitHub ↗ RU Sign in

FD Dashboard

Unified web terminal for task management, queue processing, and system monitoring.

Not recommendedcritical or high security findings · low grade F
modbender/skill-library-mcp Agent Skills author: modbender MIT 7 files · 2 scripts body ≈ 426 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Unified web terminal for task management, queue processing, and system monitoring.

As a process D 49/100 · Unfinished process — weak spots: when it triggers, inputs and preconditions, failures and branches

IntegrationData and analyticsInfrastructuretype 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
25/100
safety, quality, tests
Safety 60%
0
Quality 40%
62
Run on models
none yet
Process rating
D
49/100
Unfinished process
Inputs and preconditions w 11
0
Failures and branches w 10
0
When it triggers w 12
20
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.
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 · 23

  • high Dangerous commands cmd-persistence README.md:135
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl unload ~/Library/LaunchAgents/com.glitch.dashboard.plist
  • high Dangerous commands cmd-persistence README.md:136
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl load ~/Library/LaunchAgents/com.glitch.dashboard.plist
  • high Dangerous commands cmd-pipe-to-shell scripts/install-linux.sh:36
    Downloads and executes remote code from an unrecognised host (pipe to shell)
    curl -fsSL https://rpm.nodesource.com/setup_20.x | bash -
  • high Dangerous commands cmd-pipe-to-shell scripts/install-linux.sh:96
    Downloads and executes remote code from an unrecognised host (pipe to shell)
    curl -s https://install.zerotier.com | sudo bash
  • high Dangerous commands cmd-persistence scripts/install-macos.sh:84
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl load "$PLIST_PATH"
  • high Dangerous commands cmd-persistence scripts/install-macos.sh:94
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl load "$PLIST"
  • high Dangerous commands cmd-persistence scripts/install-macos.sh:103
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl load "$PLIST"
Medium and low: 16
  • medium Dangerous commands cmd-pipe-to-shell-known-host README.md:20
    Pipe-to-shell installer from a well-known host (still executes remote code)
    curl -fsSL https://raw.githubusercontent.com/chri…hue/glitch-skills/main/dashboard/scripts/install-linux.sh | sudo bash
  • medium Dangerous commands cmd-privilege README.md:20
    Privilege escalation / world-writable permissions
    curl -fsSL https://raw.githubusercontent.com/chri…hue/glitch-skills/main/dashboard/scripts/install-linux.sh | sudo bash
  • medium Dangerous commands cmd-pipe-to-shell-known-host README.md:26
    Pipe-to-shell installer from a well-known host (still executes remote code)
    curl -fsSL https://raw.githubusercontent.com/chri…hue/glitch-skills/main/dashboard/scripts/install-macos.sh | bash
  • medium Dangerous commands cmd-execpolicy-bypass README.md:33
    Runs PowerShell with execution policy bypassed
    powershell -ExecutionPolicy Bypass -File install.ps1
  • medium Dangerous commands cmd-pipe-to-shell-known-host scripts/install-linux.sh:32
    Pipe-to-shell installer from a well-known host (still executes remote code)
    curl -fsSL https://deb.nodesource.com/setup_20.x | bash -
  • medium Dangerous commands cmd-privilege scripts/install-linux.sh:61
    Privilege escalation / world-writable permissions
    sudo chown "$USER:$USER" "$INSTALL_DIR"
  • medium Dangerous commands cmd-privilege scripts/install-linux.sh:75
    Privilege escalation / world-writable permissions
    sudo tee /etc/systemd/system/glitch-dashboard.service > /dev/null <<EOF
  • medium Dangerous commands cmd-privilege scripts/install-linux.sh:96
    Privilege escalation / world-writable permissions
    curl -s https://install.zerotier.com | sudo bash
  • medium Dangerous commands cmd-privilege scripts/install-linux.sh:105
    Privilege escalation / world-writable permissions
    sudo tee /usr/local/bin/glitch-dashboard > /dev/null <<EOF
  • medium Dangerous commands cmd-privilege scripts/install-linux.sh:129
    Privilege escalation / world-writable permissions
    sudo chmod +x /usr/local/bin/glitch-dashboard
  • medium Dangerous commands cmd-privilege scripts/install-macos.sh:44
    Privilege escalation / world-writable permissions
    sudo cp -r glitch-skills/dashboard/* "$INSTALL_DIR/"
  • medium Dangerous commands cmd-persistence scripts/install-macos.sh:48
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
    PLIST_PATH="$HOME/Library/LaunchAgents/com.glitch.dashboard.plist"
    code literal
  • medium Dangerous commands cmd-privilege scripts/install-macos.sh:88
    Privilege escalation / world-writable permissions
    sudo tee /usr/local/bin/glitch-dashboard > /dev/null <<'EOF'
  • medium Dangerous commands cmd-persistence scripts/install-macos.sh:90
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
    PLIST="$HOME/Library/LaunchAgents/com.glitch.dashboard.plist"
    code literal
  • medium Dangerous commands cmd-privilege scripts/install-macos.sh:117
    Privilege escalation / world-writable permissions
    sudo chmod +x /usr/local/bin/glitch-dashboard
  • low Dangerous commands cmd-background-process scripts/install-linux.sh:101
    Starts a background / autostarted process
    sudo systemctl enable glitch-dashboard

Files scanned: 7. 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 49/100

  • 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
  • 30Running it twice. 1 mutating operations with no state check
  • 40Consistency. Frontmatter name (Dashboard) differs from the folder (glitch-dashboard)
  • 60Tools and files. Uses tools (bash) that frontmatter does not declare
  • 60Result and completion. Output format stated, no completion criterion
  • 100Steps. 25 steps
  • 100Execution cost. Instruction body is 426 tokens
  • 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)
  • +3Description length 82: 120–800 characters recommended
  • -2localhost URLs: will not work for another user
  • -32 of 2 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +4Structure: 13 headings
  • +3Step-by-step instructions: 25 items
  • +3Output format is stated explicitly
  • +4Has examples (1 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 62.