SKILLEMALL.ai
RU Sign in

AC remote-chrome

Launch, stop, restart, or check the status of a remote Chrome browser service using Xvfb, x11vnc, and noVNC. Use this whenever the user wants to start a headless Chrome browser accessible via web browser or VNC client, needs to stop the remote browser service, wants to restart the service, or asks for the current status/access URL of the remote browser. This is for running a full Chrome browser remotely with GUI access through a web interface.

ClawHub Agent Skills author: kelvinschen v1.0.0 MIT-0 8 files · 3 scripts body ≈ 1 145 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

As a process C 56/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches

ProcedureInfrastructuretype 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
A
90/100
safety, quality, tests
Safety 60%
93
Quality 40%
86
Run on models
none yet
Process rating
C
56/100
Has gaps
Result and completion w 14
0
Failures and branches w 10
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

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 · 7

    ✓ No critical or high findings

    Medium and low: 7
    • low Secrets in code secret-password-literal references/output-examples.md:27
      Hard-coded password / key literal (may be an example) (test fixture / example file)
      http://10.37.225.235:6080/vnc.html?host=…&port=6080&password=…&autoconnect=true
      fixture
    • low Secrets in code secret-password-literal references/output-examples.md:30
      Hard-coded password / key literal (may be an example) (test fixture / example file)
      10.37.225.235:5900 (Password: 03db…14d)
      fixture
    • low Secrets in code secret-password-literal references/output-examples.md:32
      Hard-coded password / key literal (may be an example) (test fixture / example file)
      🔑 VNC Password: 03db…14d
      fixture
    • low Secrets in code secret-password-literal references/output-examples.md:62
      Hard-coded password / key literal (may be an example) (test fixture / example file)
      http://10.37.225.235:6080/vnc.html?host=…&port=6080&password=…&autoconnect=true
      fixture
    • low Secrets in code secret-password-literal references/output-examples.md:65
      Hard-coded password / key literal (may be an example) (test fixture / example file)
      10.37.225.235:5900 (Password: 03db…14d)
      fixture
    • low Exfiltration exfil-secret-in-url start-remote-chrome.sh:414
      Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)
      echo -e "   ${CYAN}${BOLD}http://${HOST_IP}:${NOVNC_PORT}/vnc.html?host=…&port=…&password=…&autoconnect=…"
      placeholder
    • low Exfiltration exfil-secret-in-url status-remote-chrome.sh:272
      Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)
      echo -e "   ${CYAN}${BOLD}http://${HOST_IP}:${NOVNC_PORT}/vnc.html?host=…&port=…&password=…&autoconnect=…"
      placeholder

    Files scanned: 8. 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
    • 0Failures and branches. Linear process with no failure handling
    • 0Progress reporting. Says nothing while it works
    • 30Inputs and preconditions. Does not say what the process needs to start
    • 60Tools and files. Uses tools (bash) that frontmatter does not declare
    • 70When it triggers. States when to use, but not when not to
    • 100Steps. 20 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1145 tokens
    • 100Running it twice. No mutating operations

    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 447: enough signal without eating the budget
    • +4Structure: 17 headings
    • +3Step-by-step instructions: 20 items
    • +4Has examples (9 code blocks)
    • +4Reference files are cited in the instructions (3 of 3)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.

    External checks

    ClawHub: suspicious
    This skill appears to do what it says, but it exposes a live browser session and its access credentials in ways users should review carefully before installing.
    LLM: suspicious (high) · VirusTotal: · 29 May 2026