claude-mobile-ios-testing

Pass

Audited by Gen Agent Trust Hub on Feb 20, 2026

Risk Level: SAFE
Full Analysis
  • SAFE (SAFE): The skill instructions are focused on legitimate mobile automation and testing tasks. The capabilities requested, such as simulator management and package addition, are appropriate for its stated purpose.
  • Indirect Prompt Injection (SAFE): The use of AI for visual verification of screenshots presents a potential surface for indirect prompt injection from application content. Ingestion points: Results from the automation_take_screenshot tool. Boundary markers: None mentioned. Capability inventory: xc-mcp (simulator control, app installation) and expo-mcp (UI testing, package management). Sanitization: No visual data sanitization process is defined.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 20, 2026, 01:48 AM