SKILLEMALL.ai
GitHub ↗ RU Sign in

CB chromium

Launch a persistent headless Chromium with remote debugging (CDP) for browser automation — page navigation, clicks, form filling, screenshots, and cookie import. Use when the user asks to open a website, browse, click, read page content, or work with a browser.

Not recommendedcritical or high security findings
ClawHub Agent Skills author: redf426 v1.1.0 MIT-0 5 files · 1 script body ≈ 1 056 tokens Open the sourceclawhub.ai↗ analyzed 5 d ago

As a process B 73/100 · Nearly there — weak spots: result and completion, running it twice

IntegrationSoftware developmentInfrastructuretype 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
C
74/100
safety, quality, tests
Safety 60%
66
Quality 40%
85
Run on models
none yet
Process rating
B
73/100
Nearly there
Result and completion w 14
0
Running it twice w 4
30
Tools and files w 18
60
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.

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

  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.
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 · 5

  • high Dangerous commands cmd-persistence README.md:118
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    @reboot ~/.openclaw/workspace/skills/chromium/scripts/start_chromium.sh
Medium and low: 4
  • medium Exfiltration intent-browser-credential-store scripts/import_cookies.py:3
    Accesses a browser credential / cookie store (quoted — discussed, not commanded)
    Import browser cookies into the OpenClaw headless Chromium profile.
    quoted
  • medium Exfiltration intent-browser-credential-store scripts/import_cookies.py:89
    Accesses a browser credential / cookie store (detector / deny-list definition)
    parser = argparse.ArgumentParser(description="Import cookies into OpenClaw Chromium")
    detector
  • medium Dangerous commands cmd-privilege scripts/start_chromium.sh:50
    Privilege escalation / world-writable permissions
    --disable-setuid-sandbox \
  • low Dangerous commands cmd-cron-mention README.md:113
    Mentions editing / listing crontab
    crontab -e

Files scanned: 5. 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 73/100

  • 0Result and completion. Does not say what the result is
  • 30Running it twice. 1 mutating operations with no state check
  • 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 100Steps. 19 steps
  • 100When it triggers. States when to use and when not to
  • 100Failures and branches. 1 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 1056 tokens
  • 100Progress reporting. Reports progress
  • 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 261: enough signal without eating the budget
  • +4Structure: 13 headings
  • +3Step-by-step instructions: 19 items
  • +4Has examples (8 code blocks)
  • +3All 2 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.

External checks

ClawHub: suspicious
This skill appears to be a genuine Chromium automation tool, but it needs review because it can reuse logged-in browser sessions, persist account state, and run unsandboxed Chromium for arbitrary browsing.
LLM: suspicious (high) · VirusTotal: · 29 May 2026