expo-expert

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [Prompt Injection] (SAFE): No evidence of role-play instructions, safety bypass attempts, or instructions to ignore previous rules. The language is purely technical and instructional.
  • [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials or exfiltration patterns were detected. References to local storage (SQLite and File System) are aligned with the intended functionality of a mobile development skill.
  • [Obfuscation] (SAFE): No use of Base64 encoding, zero-width characters, homoglyphs, or other techniques to hide malicious intent.
  • [Unverifiable Dependencies] (SAFE): The skill references standard Expo and React Native ecosystem tools (npx expo, eas-cli) and official Expo packages. No suspicious third-party scripts or remote code execution patterns were found.
  • [Indirect Prompt Injection] (SAFE): While the skill documentation covers data persistence, there are no patterns suggesting the agent would process untrusted input in a way that leads to injection vulnerabilities. Code examples utilize SQL parameterization (e.g., ? placeholders) as a best practice.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:31 PM