swiftui-navigation

Pass

Audited by Gen Agent Trust Hub on Sep 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill demonstrates patterns for handling external URLs via deep links and universal links. This introduces a surface for indirect prompt injection if untrusted data is processed without sufficient validation.
  • Ingestion points: onOpenURL and onContinueUserActivity modifiers located in SKILL.md and references/deeplinks.md.
  • Boundary markers: The provided patterns do not include explicit prompt boundary markers or 'ignore' instructions for the agent when processing link data.
  • Capability inventory: The skill enables programmatic navigation within the application state and opening system-level URLs.
  • Sanitization: The documentation advises validating URLs before navigation, although specific implementation for input sanitization is left to the user.
  • [EXTERNAL_DOWNLOADS]: The skill references external source code repositories and documentation sites.
  • Evidence: Link to a third-party Swift library https://github.com/Dimillian/AppRouter in references/navigationstack.md and a documentation link to https://sosumi.ai/documentation/xcode/supporting-universal-links-in-your-app in references/deeplinks.md.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 11, 2026, 02:33 PM