browser-proxy

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill’s examples embed proxy usernames/passwords directly into configs, code, and proxy URLs (e.g., username/password fields and http://USER:PASS@host), which encourages the LLM to output secrets verbatim when generating configs or snippets—creating a high exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.90). This skill's SKILL.md explicitly instructs using the OpenClaw/Playwright/Puppeteer/Selenium browser tool to navigate to arbitrary public websites (e.g., page.goto('https://target-site.com') and the "After navigating with browser + proxy" extraction steps), so untrusted third‑party web content would be fetched and read as part of the workflow and could influence subsequent actions.