reviewing-hi-fi

Pass

Audited by Gen Agent Trust Hub on Jun 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized data access were detected. The skill instructions are focused on legitimate UI auditing and accessibility testing.
  • [PROMPT_INJECTION]: The skill processes untrusted code provided by users, creating a surface for indirect prompt injection. This is an inherent risk of the skill's primary function of code review.
  • Ingestion points: High-fidelity code provided as the primary input for review in Step 1 of the workflow.
  • Boundary markers: Absent; the instructions do not explicitly direct the agent to ignore instructions found within the code being analyzed.
  • Capability inventory: Leverages agent-browser (Playwright) for code rendering, Vision capabilities for visual inspection, and axe-core for accessibility audits.
  • Sanitization: No specific sanitization or escaping of the input code is defined before it is processed by the browser environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 14, 2026, 04:49 AM
Security Audit — agent-trust-hub — reviewing-hi-fi