ultimate-browsing

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This codebase intentionally includes features to extract and decrypt local browser cookies, impersonate real browsers and TLS fingerprints to bypass WAFs, and runtime-install third-party browser automation binaries — capabilities that enable credential theft and stealthy remote scraping/ access and thus constitute high-risk, dual‑use / abuse‑capable behavior.

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

• Third-party content exposure detected (high risk: 0.92). SKILL.md:12-23 routes “extract text/data from a URL / read an article” into the skill, whose runtime path python3 -m engine "<URL>" (engine/main.py:30-100) fetches outsider-authored free text (the target page’s HTML/innerText) and returns it as FetchResult.content to be included in the agent’s LLM context.