ios-rules
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a restrictive policy by explicitly banning external networking frameworks (URLSession, Alamofire), API calls, and third-party dependencies (SPM, CocoaPods). This significantly reduces the attack surface for data exfiltration and supply chain vulnerabilities.
- [SAFE]: Instructions regarding sensitive APIs such as Biometrics (Face ID), HealthKit, and Camera include requirements for proper permission descriptions (NSUsageDescriptions) and user-authorized flows, adhering to Apple's privacy guidelines.
- [SAFE]: The rules for Apple's Translation and FoundationModels frameworks emphasize on-device processing with no internet requirement, ensuring user data remains private.
- [SAFE]: The skill includes defensive coding rules, such as forbidding the hardcoding of localization dictionaries or manual language switching, which prevents common engineering errors that lead to unstable app behavior.
Audit Metadata