true-focus

Pass

Audited by Gen Agent Trust Hub on Sep 11, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes text content from HTML elements with the class .tf. It ingests this data via textContent and splits it into individual words. However, the capability set is restricted to visual DOM manipulation (toggling CSS classes), and it uses the safe s.textContent = w method to create new elements, preventing Cross-Site Scripting (XSS). No downstream capabilities like network or file access are present.
  • [SAFE]: All files (SKILL.md, true-focus.js, true-focus.css) were reviewed for malicious patterns. The JavaScript uses standard browser APIs (matchMedia, querySelectorAll, setInterval) to cycle classes for animation purposes. The author (nexu-io) and implementation align with the stated purpose of a UI animation utility.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 11, 2026, 11:51 AM
Security Audit — agent-trust-hub — true-focus