FF glance
Create, update, and manage Glance dashboard widgets. Use when user wants to: add something to their dashboard, create a widget, track data visually, show metrics/stats, display API data, or monitor usage.
As a process F 49/100 · Will not run — References files that are not bundled: references/components.md
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.
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
- 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.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- The text references files that are not there: add them or drop the references.
- 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 · 9
-
high Dangerous commands
cmd-pipe-to-shellREADME.md:49Downloads and executes remote code from an unrecognised host (pipe to shell)curl -fsSL https://openglance.dev/install.sh | bash
-
high Dangerous commands
cmd-persistenceREADME.md:100Persistence mechanism (cron / launchd / scheduled task / autorun registry)launchctl unload ~/Library/LaunchAgents/com.glance.dashboard.plist
-
high Dangerous commands
cmd-persistenceREADME.md:103Persistence mechanism (cron / launchd / scheduled task / autorun registry)launchctl load ~/Library/LaunchAgents/com.glance.dashboard.plist
-
high Dangerous commands
cmd-persistenceSKILL.md:73Persistence mechanism (cron / launchd / scheduled task / autorun registry)cat > ~/Library/LaunchAgents/com.glance.dashboard.plist << 'EOF'
-
high Dangerous commands
cmd-persistenceSKILL.md:102Persistence mechanism (cron / launchd / scheduled task / autorun registry)launchctl load ~/Library/LaunchAgents/com.glance.dashboard.plist
-
high Dangerous commands
cmd-persistenceSKILL.md:107Persistence mechanism (cron / launchd / scheduled task / autorun registry)launchctl unload ~/Library/LaunchAgents/com.glance.dashboard.plist
Medium and low: 3
-
low Exfiltration
read-dotenvSKILL.md:40Reads a .env filecp .env.example .env.local
-
low Secrets in code
secret-github-tokenwidget-sdk.md:585GitHub token (placeholder value)"value": "ghp_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
placeholder -
low Exfiltration
net-credential-usewidget-sdk.md:2029Credential used in a network call (verify the destination is the intended service) (destination is a well-known publishing service; quoted — discussed, not commanded)"server_code": "const token = await getCredential('github');\nconst response = await fetch('https://api.github.com/repos/acfranzen/libra/pulls?state=open', {\n headers: { Authorization: `Bearer ${tokknown servicequoted
Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 7188 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: references/components.md
Process rating: all ten parameters 49/100
- 0Tools and files. 1 referenced file(s) missing: references/components.md
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 21 mutating operations with no state check
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 7188 tokens
- 100Steps. 64 steps
- 100Failures and branches. 3 branches, has a failure section
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 20 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (5 tags): a typed call is more reliable
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
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +3Description length 204: enough signal without eating the budget
- +4Structure: 41 headings
- +3Step-by-step instructions: 64 items
- +4Has examples (37 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.