SKILLEMALL.ai

AC safari-control

Use Safari directly on macOS when work must happen in the user's real Safari session instead of a separate automation browser. Best for reading the current tab, inspecting the live session layout, operating Safari menu bar or native toolbar controls, reading page text and structure, running page JavaScript, waiting for page conditions, exporting page artifacts, and performing lightweight DOM interactions in the active Safari tab. If Safari JavaScript from Apple Events is disabled, guide the user to enable it or fall back to desktop-control for visual interaction.

ClawHub Agent Skills author: Gordonynh v1.0.1 MIT-0 3 files body ≈ 3 211 tokens Open the sourceclawhub.ai analyzed 3 d ago

As a process C 63/100 · Has gaps — weak spots: result and completion, inputs and preconditions

ReferenceSoftware developmentInfrastructuretype and topics are labelled automatically from the skill text
JSON
Technical rating
A
91/100
safety, quality, tests
Safety 60%
95
Quality 40%
84
Run on models
none yet
Process rating
C
63/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
30
When it triggers w 12
50
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Exfiltration medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

How to improve

    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 · 1

    ✓ No critical or high findings

    Medium and low: 1
    • medium Exfiltration intent-browser-credential-store skill-card.md:14
      Accesses a browser credential / cookie store (quoted — discussed, not commanded)
      Developers, engineers, and agents use this skill to inspect and operate the user's real Safari session on macOS when logged-in state, cookies, open tabs, Safari chrome, or live page content matter. It
      quoted

    Files scanned: 2. 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 63/100

    • 0Result and completion. Does not say what the result is
    • 30Inputs and preconditions. Does not say what the process needs to start
    • 50When it triggers. No condition that starts the skill
    • 60Tools and files. Uses tools (bash) that frontmatter does not declare
    • 85Steps. 50 steps, 1 vague phrases
    • 100Failures and branches. 6 branches, has a failure section
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 3211 tokens
    • 100Running it twice. Mutating operations check current state
    • 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)
    • +3Output format is not stated: the model decides each time
    • +1No license
    • +2Single-language instructions
    • +3Description length 569: enough signal without eating the budget
    • +4Structure: 16 headings
    • +3Step-by-step instructions: 50 items
    • +4Has examples (13 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.

    External checks

    ClawHub: suspicious
    This Safari automation skill is coherent, but it gives an agent high-risk access to the user’s real logged-in Safari session, including raw cookie and browser-storage export, without enough built-in warning or consent controls.
    LLM: suspicious (high) · VirusTotal: · 29 May 2026