mobile-rn-screen

Pass

Audited by Gen Agent Trust Hub on Jul 24, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands via the Android Debug Bridge (adb) to capture screenshots and modify emulator display dimensions (e.g., adb shell wm size 412x917). These operations are standard practices for mobile interface testing and are limited to the connected development device.
  • [COMMAND_EXECUTION]: Provides instructions for testing deep link navigation using adb shell am start, which is a legitimate diagnostic procedure for verifying navigation stack initialization.
  • [INDIRECT_PROMPT_INJECTION]: The skill involves reading and processing external source code files (e.g., .tsx screen files and API entity definitions). While this creates an ingestion surface for untrusted data, the skill uses this information for local analysis and UI improvement recommendations without high-risk capabilities like network exfiltration or direct file writes based on that data.
  • [EXTERNAL_DOWNLOADS]: References several well-known and trusted community libraries (such as Shopify's FlashList and Skia, and React Navigation) as recommended primitives for performance and accessibility improvements.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 24, 2026, 11:19 AM
Security Audit — agent-trust-hub — mobile-rn-screen