SKILLEMALL.ai
RU Sign in

CC stable-browser

Set up reliable browser automation using Chrome DevTools Protocol (CDP) instead of the flaky browser extension relay. Use when browser relay keeps disconnecting, throwing WebSocket 403 errors, or when you need stable headless/headed browser control for web scraping, form filling, social media posting, or any browser automation task. Replaces profile="chrome" with a rock-solid CDP connection.

Not recommendedcritical or high security findings
ClawHub Agent Skills author: jarvis563 v1.0.0 4 files · 1 script body ≈ 670 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

As a process C 55/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

ReferenceInfrastructureMarketingtype 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
72/100
safety, quality, tests
Safety 60%
59
Quality 40%
91
Run on models
none yet
Process rating
C
55/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
When it triggers w 12
20
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
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 · 3

  • high Dangerous commands cmd-persistence scripts/setup-cdp.sh:118
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl load "$PLIST_PATH" 2>/dev/null || true
  • high Exfiltration intent-browser-credential-store SKILL.md:57
    Accesses a browser credential / cookie store
    | Auth/Cookies | Shares your main Chrome | Dedicated profile |
Medium and low: 1
  • medium Dangerous commands cmd-persistence scripts/setup-cdp.sh:11
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
    PLIST_PATH="$HOME/Library/LaunchAgents/com.openclaw.chrome-cdp.plist"
    code literal

Files scanned: 4. 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 55/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 4 mutating operations with no state check
  • 60Tools and files. Uses tools (bash) that frontmatter does not declare
  • 100Steps. 22 steps
  • 100Failures and branches. 2 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 670 tokens
  • 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 394: enough signal without eating the budget
  • +4Structure: 10 headings
  • +3Step-by-step instructions: 22 items
  • +4Has examples (2 code blocks)
  • +4Reference files are cited in the instructions (1 of 1)
  • +3All 1 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.

External checks

ClawHub: suspicious
This skill appears to do what it says, but it enables a persistent Chrome debugging profile that can control logged-in browser sessions and does not give users enough opt-in or removal guidance.
LLM: suspicious (medium) · VirusTotal: benign · 28 May 2026