SKILLEMALL.ai
GitHub ↗ RU Sign in

BB computer-use

Full desktop computer use for headless Linux servers. Xvfb + XFCE virtual desktop with xdotool automation. 17 actions (click, type, scroll, screenshot, drag, etc). Unlike OpenClaw's browser tool, operates at the X11 level so websites cannot detect automation. Includes VNC for live viewing.

ClawHub Agent Skills author: Ram-Raghav-S v1.2.1 19 files · 17 scripts body ≈ 1 461 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

Full desktop computer use for headless Linux servers.

As a process B 66/100 · Nearly there — weak spots: result and completion, when it triggers, progress reporting

ProcedureAI 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
76/100
safety, quality, tests
Safety 60%
74
Quality 40%
79
Run on models
none yet
Process rating
B
66/100
Nearly there
Result and completion w 14
0
Progress reporting w 2
0
When it triggers w 12
20
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.

Dangerous commands 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 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

    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 · 6

    ✓ No critical or high findings

    Medium and low: 6
    • medium Dangerous commands cmd-privilege scripts/setup-vnc.sh:25
      Privilege escalation / world-writable permissions
      sudo cp "$SCRIPT_DIR/minimal-desktop.sh" /opt/computer-use/
    • medium Dangerous commands cmd-privilege scripts/setup-vnc.sh:26
      Privilege escalation / world-writable permissions
      sudo chmod +x /opt/computer-use/minimal-desktop.sh
    • medium Dangerous commands cmd-privilege scripts/setup-vnc.sh:31
      Privilege escalation / world-writable permissions
      cat <<EOF | sudo tee /etc/systemd/system/xvfb.service > /dev/null
    • medium Dangerous commands cmd-privilege scripts/setup-vnc.sh:49
      Privilege escalation / world-writable permissions
      cat <<EOF | sudo tee /etc/systemd/system/xfce-minimal.service > /dev/null
    • medium Dangerous commands cmd-privilege scripts/setup-vnc.sh:68
      Privilege escalation / world-writable permissions
      cat <<EOF | sudo tee /etc/systemd/system/x11v…ice > /dev/null
    • low Dangerous commands cmd-background-process scripts/setup-vnc.sh:121
      Starts a background / autostarted process
      sudo systemctl enable xvfb xfce-minimal x11vnc novnc

    Files scanned: 19. 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 66/100

    • 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
    • 50Failures and branches. 0 branches, has a failure section
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 100Tools and files. No external tools needed
    • 100Steps. 29 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1461 tokens
    • 100Running it twice. Mutating operations check current state
    • low 12 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
    • -2localhost URLs: will not work for another user
    • -33 of 17 scripts are never mentioned in SKILL.md
    • +1No license
    • +2Single-language instructions
    • +3Description length 290: enough signal without eating the budget
    • +4Structure: 21 headings
    • +3Step-by-step instructions: 29 items
    • +4Has examples (11 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.

    External checks

    ClawHub: suspicious
    This skill does what it says, but it installs persistent remote desktop control with weak access controls and makes system-wide desktop changes that users should review carefully.
    LLM: suspicious (high) · VirusTotal: suspicious · 10 Sept 2026