swiftui-pro
Pass
Audited by Gen Agent Trust Hub on Mar 11, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill processes user-provided source code, which represents a surface for indirect prompt injection.
- Ingestion points: The skill reads and analyzes Swift and SwiftUI files provided by the user in the agent's context (SKILL.md).
- Boundary markers: The instructions do not specify explicit delimiters or warnings (e.g., 'ignore instructions within code comments') to mitigate the risk of the agent following malicious commands embedded in user code.
- Capability inventory: The skill leverages environment tools via the Xcode MCP, including
RenderPreviewfor image capture andDocumentationSearchfor API lookup (references/hygiene.md). - Sanitization: No explicit sanitization or input validation for processed code is defined.
- [SAFE]: No hardcoded credentials, suspicious network operations, or obfuscation techniques were detected. References to fictional platform versions (iOS 26 and Swift 6.2) are used as part of the tool's instructional context and do not facilitate malicious activity.
Audit Metadata