NYC

mobile-responsiveness

Pass

Audited by Gen Agent Trust Hub on Feb 15, 2026

Risk Level: LOW
Full Analysis
  • [SAFE] (SAFE): No malicious patterns or vulnerabilities detected.
  • The skill contains purely declarative code (CSS, HTML) and standard React component logic (TSX) for UI development.
  • Category 1 (Prompt Injection): No instructions attempting to override agent behavior or safety filters were found.
  • Category 2 (Data Exposure): No hardcoded credentials, sensitive file paths, or network operations are present.
  • Category 4 & 10 (Remote/Dynamic Code): No external dependencies are installed and no dynamic execution sinks (like eval) are used.
  • Category 8 (Indirect Prompt Injection): While the skill includes hooks that accept strings (like queries), it lacks any 'sink' capabilities (file write, network, command execution) that could be exploited.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 15, 2026, 10:17 PM