Nextbrowser

Security checks across malware telemetry and agentic risk

Overview

The skill is designed for autonomous online-account browser automation using persistent logins, residential proxies, stealth browsing, and CAPTCHA solving, which can evade website protections.

Treat this as a high-risk automation skill. It may be appropriate only for tightly controlled, authorized browser testing or account-management workflows; avoid using it for stealth, CAPTCHA bypass, residential-proxy evasion, or autonomous actions on social media and other logged-in accounts without explicit review.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Risk analysis

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

#
ASI02: Tool Misuse and Exploitation
Critical
What this means

Installing it could let an agent automate logged-in accounts in ways that websites may treat as abusive or evasive, risking account bans, unwanted public actions, or policy violations.

Why it was flagged

This combines autonomous browser control, persistent account sessions, residential proxies, stealth, and CAPTCHA solving. That is materially different from ordinary browser automation because it can bypass website anti-bot and account-protection controls.

Skill content
Primary use is creating browser sessions with profiles (persisted logins/cookies) that Openclaw can control to manage social media and other online accounts. Secondary use is running task subagents for fast autonomous browser automation under residential proxy, browser stealth, and CAPTCHA solving capability.
Recommendation

Do not install unless you have a legitimate, authorized use and can enforce explicit per-task approval, target-site limits, rate limits, and no anti-detection or CAPTCHA-bypass use.

#
ASI03: Identity and Privilege Abuse
High
What this means

An agent using this skill could act through your Nextbrowser account and through logged-in website sessions stored in profiles.

Why it was flagged

The skill uses a provider API key and persistent login/cookie profiles that can represent real online-account identities. The artifacts do not clearly bound which accounts may be controlled or what actions require user approval.

Skill content
**API Key** is read from openclaw config at `skills.entries.next-browser.apiKey`... Profiles persist cookies and login state across browser sessions.
Recommendation

Use a dedicated, least-privileged API key and separate browser profiles; require confirmation before creating, deleting, starting, or using logged-in profiles.

#
ASI10: Rogue Agents
High
What this means

Browser sessions or autonomous tasks could continue consuming credits or acting through logged-in profiles longer than the user intended.

Why it was flagged

The skill contemplates autonomous subagents and long-running cloud browser instances. Although start/stop endpoints are documented, the artifacts do not define strict task boundaries, runtime caps, or mandatory cleanup.

Skill content
Secondary use is running task subagents for fast autonomous browser automation... Start browser for profile (creates browser instance)... Stop browser for profile
Recommendation

Require explicit stop conditions, time limits, credit limits, and cleanup checks for every browser session or autonomous task.