SKILLEMALL.ai
RU Sign in

AC browser-mcp-agent

Give an AI agent its own real browser over MCP tool calls - launch, navigate, click, fill, screenshot, extract text, run JS - with a kernel-level real-device fingerprint and a persistent profile, so the session stays logged in between runs and pages see one coherent device instead of a headless build. No Playwright or SDK code to write. Use when an agent should operate a site itself, when a computer-use / browser-use setup needs a captured real fingerprint rather than a synthetic one, when agent sessions keep losing their login, or when comparing hosted agent-browser services. Also for 'MCP browser', 'browser MCP server', 'let my agent browse the web', 'agent browser control', 'browser-use MCP', 'computer use browser', 'Browserbase alternative', 'Steel browser alternative', 'headless browser detected'. Node (npx) or Python; Windows x64, macOS Intel + Apple Silicon, Linux x64 / arm64. SDK and REST reference is anti-detect-browser; account isolation is multi-account-isolation.

ClawHub Agent Skills author: antibrow v1.0.3 MIT-0 3 files body ≈ 3 250 tokens Open the sourceclawhub.ai↗ analyzed 34 h ago

Give an AI agent its own real browser over MCP tool calls - launch, navigate, click, fill, screenshot, extract text, run JS - with a kernel-level real-device…

As a process C 52/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice

IntegrationPlaywrightAI 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
A
90/100
safety, quality, tests
Safety 60%
95
Quality 40%
82
Run on models
none yet
Process rating
C
52/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Running it twice w 4
30
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.

Instruction override 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 text contains phrases like "ignore previous instructions" or "you are now…". That is an attempt to hijack the agent: it may break your rules, the system limits or company policy.

For the author

An honest skill does not need them: state the role and the rules directly without overriding other instructions. Otherwise catalog scanners and corporate filters will block the listing.

How to improve

    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 Instruction override en-ignore-previous SKILL.md:131
      Instruction-override phrase ("ignore previous instructions") (detector / deny-list definition)
      In MCP mode the agent is both reading pages and choosing the next tool call, which is exactly the condition indirect prompt injection needs. A page can carry text written to be read by an agent: "igno
      detector

    Files scanned: 3. 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 52/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 30Running it twice. 9 mutating operations with no state check
    • 50When it triggers. No condition that starts the skill
    • 55Failures and branches. 1 branches
    • 60Tools and files. Uses tools (web, python, node) that frontmatter does not declare
    • 85Steps. 32 steps, 1 vague phrases
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 3250 tokens
    • 100Progress reporting. Reports progress
    • low 11 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)
    • +3Description length 989: 120–800 characters recommended
    • +3Output format is not stated: the model decides each time
    • +2Single-language instructions
    • +4Structure: 13 headings
    • +3Step-by-step instructions: 32 items
    • +4Has examples (3 code blocks)
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.

    External checks

    ClawHub: clean
    The skill is a high-capability browser-control integration, but its persistent profiles, JavaScript execution, live view, external binary, and API-key use are clearly disclosed and aligned with its stated purpose.
    LLM: benign (high) · VirusTotal: · 6 Aug 2026