stealth-browser-launch

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill's examples embed credentials directly in proxy URLs (e.g., "http://user:pass@residential-proxy:port"), which encourages including secret values verbatim in generated code/commands and risks secret exfiltration.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This document describes tools and procedures explicitly designed to evade anti-bot defenses (CAPTCHAs, Cloudflare, FingerprintJS) and to enable stealthy, persistent, multi-identity automated access to protected targets—behavior intended to bypass security controls and facilitate abuse.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (low risk: 0.10). The required runtime workflow only launches and interacts with a user-specified browsing target via Playwright (e.g., page.goto("https://target.com")), so outsider-authored free text is ingested only through that chosen external website, not unconditionally by the skill itself.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 0.80). The skill instructs the user to run system-level installation and runtime commands (e.g., pip install playwright && playwright install-deps chromium, apt install -y ..., docker run -d ..., and starting Xvfb) which modify the host system state and may require elevated privileges.