NYC

react-native-app

Pass

Audited by Gen Agent Trust Hub on Feb 15, 2026

Risk Level: LOW
Full Analysis
  • [Prompt Injection] (SAFE): No instructions attempting to override agent behavior or bypass safety guidelines were found.
  • [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials or access to sensitive local files. Network operations are directed to example API endpoints and represent standard development patterns.
  • [Obfuscation] (SAFE): No hidden or encoded content, zero-width characters, or homoglyphs detected.
  • [Unverifiable Dependencies & Remote Code Execution] (SAFE): No remote scripts or unauthorized package installations are present. Use of standard libraries is consistent with the skill's purpose.
  • [Indirect Prompt Injection] (SAFE): The skill provides code templates and does not possess an attack surface for ingesting untrusted external data that could influence agent behavior.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 15, 2026, 09:14 PM