Skills
Navigate
skills/revitalb-port/skills-registry-demo/dark-mode-testing/Gen Agent Trust Hub

dark-mode-testing

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill interacts with external website content which could theoretically contain malicious instructions.
  • Ingestion points: External websites loaded via browser_navigate and inspected via browser_snapshot (SKILL.md).
  • Boundary markers: None identified between the browser's content and the agent's instructions.
  • Capability inventory: Browser navigation, screenshot capture, and JavaScript execution within the browser context.
  • Sanitization: No specific content sanitization is described for the external page data.
  • [DYNAMIC_EXECUTION]: The skill uses JavaScript execution to toggle themes on the target page.
  • The instructions provide specific snippets for class and attribute toggling (classList.toggle('dark'), setAttribute('data-theme', 'dark')) which are executed within the browser's sandbox to manipulate the DOM for testing purposes.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 04:54 PM