SKILLEMALL.ai
GitHub ↗ RU Sign in

BD realbrowser

Lets your AI agent drive a real Chrome session (yours or a marketplace participant's) for tasks where headless or scripted requests are not enough — your own QA flows, accessibility audits of sites you control, synthetic monitoring, support-dashboard automation, and data collection on sites whose Terms of Service and robots.txt permit it.

ClawHub Agent Skills author: iWedmak Om v0.1.1 MIT-0 14 files · 1 script body ≈ 3 460 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

Lets your AI agent drive a real Chrome session (yours or a marketplace participant's) for tasks where headless or scripted requests are not enough — your own…

As a process D 48/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, failures and branches

IntegrationGitHubCommerceAI and agentsInfrastructuretype 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
85/100
safety, quality, tests
Safety 60%
93
Quality 40%
73
Run on models
none yet
Process rating
D
48/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
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

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
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

✓ No critical or high findings

Medium and low: 3
  • medium Exfiltration intent-browser-credential-store clawhub-listing.md:89
    Accesses a browser credential / cookie store (documentation of a security skill)
    - **Self mode** does not transmit user's Chrome data to third parties — sessions are routed through Ceki's dispatcher only for agent task execution, and the server is stateless between rentals (cookie
    security skill
  • low Exfiltration net-credential-use SKILL.md:277
    Credential used in a network call (verify the destination is the intended service) (documentation of a security skill)
    curl -s -H "Authorization: Bearer $CEKI_API_KEY" https://api.ceki.me/api/auth/introspect | jq '.tokenable_id, .name'
    security skill
  • low Exfiltration net-credential-use SKILL.md:279
    Credential used in a network call (verify the destination is the intended service) (documentation of a security skill)
    curl -s -H "Authorization: Bearer $CEKI_API_KEY" https://api.ceki.me/api/browsers/search | jq '.meta.total'
    security skill

Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")

Process rating: all ten parameters 48/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 0Progress reporting. Says nothing while it works
  • 50When it triggers. No condition that starts the skill
  • 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
  • 85Steps. 47 steps, 1 vague phrases
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 3460 tokens
  • 100Running it twice. Mutating operations check current state
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 23 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (15 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
  • +2Single-language instructions
  • +3Description length 340: enough signal without eating the budget
  • +4Structure: 28 headings
  • +3Step-by-step instructions: 47 items
  • +4Has examples (13 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 73.

External checks

ClawHub: suspicious
This is a disclosed real-browser automation skill, but it needs review because it can rent and drive live browser sessions, handle session profiles, and one example pre-approves high-impact actions without per-action user approval.
LLM: suspicious (medium) · 20 Jun 2026