swiftui-pro
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze and review user-provided Swift and SwiftUI source code. This creates a surface for indirect prompt injection if the code being reviewed contains malicious instructions hidden in comments or strings.\n
- Ingestion points: The agent reads and processes Swift source files as directed by the user.\n
- Boundary markers: The skill does not define clear boundaries or instructions to ignore embedded prompts within the code being analyzed.\n
- Capability inventory: The skill performs code analysis and provides reporting; it also utilizes external tools like
RenderPreviewandDocumentationSearchif the Xcode MCP is available.\n - Sanitization: No specific input sanitization or filtering is applied to the code content before analysis.\n- [EXTERNAL_DOWNLOADS]: The skill documentation includes references to related agent skills hosted on GitHub. These links are provided as helpful suggestions for specialized tasks like SwiftData, Concurrency, and Testing.\n
- Evidence: References to
github.com/twostraws/swiftdata-agent-skill,github.com/twostraws/swift-concurrency-agent-skill, andgithub.com/twostraws/swift-testing-agent-skillin the reference files.
Audit Metadata