mobile-design
Pass
Audited by Gen Agent Trust Hub on May 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: Detailed inspection of the skill's instructions and reference files shows they are exclusively dedicated to mobile development best practices (UX, performance, and security). The content explicitly warns against security 'sins' such as storing tokens in insecure storage or hardcoding API keys.
- [COMMAND_EXECUTION]: The skill provides an audit script (
scripts/mobile_audit.py) intended for execution via the Bash tool. Analysis of the source code confirms it performs read-only regex-based scanning of local files in a user-provided directory. It does not perform network operations, file modifications, or access sensitive system paths. - [DATA_EXFILTRATION]: No patterns associated with data exfiltration or credential harvesting were found. The Python script uses only the standard library (os, re, sys, json) and lacks the capability to transmit data over a network.
- [PROMPT_INJECTION]: The skill uses 'Anti-Memorization' and 'Thinking Protocol' instructions designed to force the AI to reason about mobile-specific constraints rather than relying on generic web-development training data. These instructions do not attempt to bypass safety filters or disregard system instructions.
Audit Metadata