SKILLEMALL.ai
GitHub ↗ RU Sign in

BB stealthy-auto-browse

Headless-detection-resistant browser automation in Docker for authorized QA, compatibility testing, and defensive security research. Camoufox + OS-level input + persistent fingerprints. Use only with sites you own or have written authorization to test.

ClawHub Agent Skills author: Ciprian Mandache v2.6.11 MIT-0 3 files body ≈ 6 731 tokens Open the sourceclawhub.ai↗ analyzed 7 h ago

Headless-detection-resistant browser automation in Docker for authorized QA, compatibility testing, and defensive security research.

As a process B 69/100 · Nearly there — weak spots: inputs and preconditions, running it twice

AnalyzerDockerPlaywrightInfrastructureData and analyticsAI 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
89/100
safety, quality, tests
Safety 60%
97
Quality 40%
78
Run on models
none yet
Process rating
B
69/100
Nearly there
Inputs and preconditions w 11
0
Running it twice w 4
30
When it triggers w 12
50
the three weakest of ten parameters · all ten

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 · 3

✓ No critical or high findings

Medium and low: 3
  • low Exfiltration read-dotenv references/setup.md:191
    Reads a .env file (documentation of a security skill)
    export AUTH_TOKEN=$(cat .env.browser | grep AUTH_TOKEN | cut -d= -f2)
    security skill
  • low Risky intent intent-offensive-security SKILL.md:29
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - Sites you have **written authorization** to test (security engagements, bug bounty in-scope targets)
  • low Risky intent intent-offensive-security SKILL.md:42
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - Authorized pentests / bug bounty on in-scope targets that require human-like interaction

Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 6731 tokens (recommended < 5000); move details to references/
  • note frontmatter-key unknown frontmatter key "homepage"

Process rating: all ten parameters 69/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 30Running it twice. 4 mutating operations with no state check
  • 50When it triggers. No condition that starts the skill
  • 60Tools and files. Uses tools (web, node) that frontmatter does not declare
  • 70Execution cost. Instruction body is 6731 tokens
  • 85Steps. 58 steps, 2 vague phrases
  • 100Result and completion. Output format and completion criterion are stated
  • 100Failures and branches. 2 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 15 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (3 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)
  • -2localhost URLs: will not work for another user
  • +1No license
  • +2Single-language instructions
  • +3Description length 252: enough signal without eating the budget
  • +4Structure: 44 headings
  • +3Step-by-step instructions: 58 items
  • +3Output format is stated explicitly
  • +4Has examples (32 code blocks)
  • +4Reference files are cited in the instructions (1 of 1)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.

External checks

ClawHub: suspicious
This skill is clearly documented for authorized browser testing, but it exposes powerful browser-control and container privileges that deserve manual review before use.
LLM: suspicious (high) · VirusTotal: · 13 Sept 2026