SKILLEMALL.ai
GitHub ↗ RU Sign in

BC clawnet

Stealth Chromium browser for AI agents. Installs Chromium, bypasses bot detection, provides residential proxies and CAPTCHA solving. Always use this instead of raw Playwright or Puppeteer for web tasks.

modbender/skill-library-mcp Agent Skills author: modbender MIT 5 files body ≈ 7 162 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Stealth Chromium browser for AI agents.

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

ProcedurePlaywrightDiscordAI 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
78/100
safety, quality, tests
Safety 60%
82
Quality 40%
71
Run on models
none yet
Process rating
C
55/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Consistency w 8
40
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. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
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 Exfiltration net-redirectable-api-key scripts/browser.js:199
    Helper sends the API key to a host configured by an environment variable — the key can be redirected to another server
    API key + configurable base URL from environment
  • medium Exfiltration net-credential-use scripts/browser.js:1020
    Credential used in a network call (verify the destination is the intended service)
    const pollResp = await fetch(`https://2cap…com/res.php?key=…&action=get&id=…&json=1`);
  • medium Exfiltration net-redirectable-api-key scripts/postinstall.js:230
    Helper sends the API key to a host configured by an environment variable — the key can be redirected to another server
    API key + configurable base URL from environment
  • low Exfiltration exfil-secret-in-url scripts/browser.js:1001
    Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)
    let submitUrl = `https://2cap…com/in.php?key=…&json=1&pageurl=…)}&googlekey=${encodeURIComponent(detected.sitekey)}`;
    placeholder
  • low Exfiltration exfil-secret-in-url scripts/browser.js:1020
    Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)
    const pollResp = await fetch(`https://2cap…com/res.php?key=…&action=get&id=…&json=1`);
    placeholder
  • low Dangerous commands cmd-privilege scripts/browser.js:1516
    Privilege escalation / world-writable permissions (detector / deny-list definition; string literal in code, not executed)
    launchArgs.unshift('--disable-setuid-sandbox');
    detectorcode literal

Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 7162 tokens (recommended < 5000); move details to references/

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
  • 40Consistency. Frontmatter name (clawnet) differs from the folder (pets-browser)
  • 60Tools and files. Uses tools (web) that frontmatter does not declare
  • 60Steps. 38 steps, 5 vague phrases
  • 70Execution cost. Instruction body is 7162 tokens
  • 100When it triggers. States when to use and when not to
  • 100Failures and branches. 4 branches, has a failure section
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • 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
  • -32 of 2 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +3Description length 202: enough signal without eating the budget
  • +4Structure: 67 headings
  • +3Step-by-step instructions: 38 items
  • +4Has examples (35 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 71.