responsiveness-check

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill performs legitimate automated UI testing using established tools such as Playwright and Chrome MCP. All file operations and network requests are within the scope of its documented functionality.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data by visiting third-party websites, creating a surface for potential indirect prompt injection.
  • Ingestion points: The skill navigates to and renders HTML/CSS from external URLs provided by the user.
  • Boundary markers: No specific delimiters or safety instructions are defined to separate untrusted website content from the agent's internal analysis logic.
  • Capability inventory: The skill utilizes browser automation for navigation and resizing, captures screenshots, and writes markdown reports to the local file system (docs/).
  • Sanitization: Not specified, though the skill's focus is on visual layout properties (width, overflow, stacking) rather than executing or interpreting textual content from the page.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 03:16 PM
Security Audit — agent-trust-hub — responsiveness-check