responsive-testing

Pass

Audited by Gen Agent Trust Hub on Apr 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill defines a legitimate developer workflow for UI/UX verification. It utilizes standard browser automation tools (navigation, snapshots, and screenshots) to ensure layout consistency.
  • [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it ingests untrusted data from web pages via browser_snapshot.
  • Ingestion points: External web content retrieved through browser_navigate and browser_snapshot (SKILL.md).
  • Boundary markers: Absent; the agent is instructed to read the aria tree and visual layout directly.
  • Capability inventory: The skill uses browser_navigate, browser_snapshot, and browser_take_screenshot (SKILL.md).
  • Sanitization: No sanitization of page content is performed before processing. However, given the skill's primary use case for local development testing, this risk is minimal.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 12, 2026, 09:42 PM
Security Audit — agent-trust-hub — responsive-testing