skills/thienqo/ios-skills/mapkit/Gen Agent Trust Hub

mapkit

Pass

Audited by Gen Agent Trust Hub on Oct 9, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The analyzed skill consists entirely of technical documentation, architectural patterns, and code examples for iOS location services. No malicious patterns, obfuscation, or unauthorized data access were detected.
  • [INDIRECT_PROMPT_INJECTION]: The skill documents implementation patterns that process user-supplied strings for search and geocoding operations, representing a standard injection surface.
  • Ingestion points: The skill utilizes MKLocalSearch.Request.naturalLanguageQuery, CLGeocoder.geocodeAddressString, and MKLocalSearchCompleter.queryFragment to process external input in references/core-implementation.md and references/mapkit-patterns.md.
  • Boundary markers: No specific delimiters or boundary markers are defined for these input strings; however, the skill recommends performance-oriented patterns such as debouncing and task cancellation to manage the processing lifecycle.
  • Capability inventory: Capabilities are restricted to high-level system framework APIs (MapKit, CoreLocation) which do not provide direct paths for arbitrary command execution or file system modification.
  • Sanitization: The skill relies on standard Apple framework handling for search queries without defining custom sanitization logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 9, 2026, 12:01 PM