SKILLEMALL.ai
GitHub ↗ RU Sign in

BF ManoBrowser

Your hands in the user's real browser. Operate the user's own Chrome with their logged-in sessions — extract data behind login walls, reverse-engineer website APIs into reusable skills, and automate any browser workflow. Use when you need login-required data extraction, API reverse engineering, browser automation, or social media data collection. 给你一双手，像用户一样使用浏览器。在用户已登录的 Chrome 中工作——提取登录墙后的数据、逆向 API 生成可复用 Skill、自动化浏览器工作流。

ClawHub Agent Skills author: Sophieyou v2.2.7 MIT-0 28 files body ≈ 2 642 tokens Open the sourceclawhub.ai↗ analyzed 4 d ago

As a process F 35/100 · Will not run — References files that are not bundled: browser-automation/SKILL.md, web-data-extractor/SKILL.md, platform-data-explorer/SKILL.md

ProcedureInfrastructureMarketingtype 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
81/100
safety, quality, tests
Safety 60%
95
Quality 40%
60
Run on models
none yet
Process rating
F
35/100
Will not run
References files that are not bundled: browser-automation/SKILL.md, web-data-extractor/SKILL.md, platform-data-explorer/SKILL.md
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
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. The text references files that are not there: add them or drop the references.
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 · 1

✓ No critical or high findings

Medium and low: 1
  • medium Exfiltration intent-browser-credential-store skill-card.md:2
    Accesses a browser credential / cookie store (detector / deny-list definition)
    ManoBrowser lets agents operate a user's logged-in Chrome through a Chrome extension and MCP connection to extract web data, reverse-engineer web APIs, and build reusable browser automation workflows.
    detector

Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning name-format name should be kebab-case (lowercase letters, digits, hyphens)
  • warning missing-ref reference to a missing file: browser-automation/SKILL.md
  • warning missing-ref reference to a missing file: web-data-extractor/SKILL.md
  • warning missing-ref reference to a missing file: platform-data-explorer/SKILL.md
  • warning missing-ref reference to a missing file: api-skill-builder/SKILL.md
  • warning missing-ref reference to a missing file: chrome-workflow-build/SKILL.md

Process rating: all ten parameters 35/100

Will not run. References files that are not bundled: browser-automation/SKILL.md, web-data-extractor/SKILL.md, platform-data-explorer/SKILL.md
  • 0Tools and files. 5 referenced file(s) missing: browser-automation/SKILL.md, web-data-extractor/SKILL.md, platform-data-explorer/SKILL.md
  • 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
  • 20When it triggers. No condition that starts the skill
  • 100Steps. 92 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 2642 tokens
  • 100Running it twice. No mutating operations
  • low 10 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
  • -5TODO / placeholder text left in the skill
  • -237 emoji in the instructions: noise for the model
  • +1No license
  • +2Single-language instructions
  • +3Description length 425: enough signal without eating the budget
  • +4Structure: 32 headings
  • +3Step-by-step instructions: 92 items
  • +4Has examples (9 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 60.

External checks

ClawHub: suspicious
ManoBrowser is a disclosed browser automation skill, but it needs Review because it can control logged-in Chrome sessions, use cookies, collect sensitive page data, and persist detailed workflow artifacts with uneven consent and redaction safeguards.
LLM: suspicious (high) · VirusTotal: · 28 May 2026