The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill provides patterns for building URL and notification resolvers that ingest untrusted external data, creating a potential surface for indirect prompt injection.
Ingestion points: The URLDeepLinkResolving and NotificationDeepLinkResolving protocols in references/deep-links-and-universal-links.md process external URLs and notification payloads.
Boundary markers: No specific boundary markers or delimiters for the LLM are implemented in the code snippets, though structural parsing is encouraged.
Capability inventory: The integration is scoped to navigation state management (stack pushes, modal presentations, and alerts).
Sanitization: The skill explicitly recommends validating schemes, hosts, and segments, and using explicit validation errors rather than silent fallbacks.
[EXTERNAL_DOWNLOADS]: The documentation includes instructions to download and install the skill from a remote repository.
Evidence: npx skills add https://github.com/Erikote04/SwiftNavigation --skill skill in README.md.
Context: The command fetches content from the author's own repository on GitHub, which is a well-known service. This is a standard installation pattern for this type of extension.

swift-navigation-skill