swiftui-performance
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes user-supplied SwiftUI source code and performance traces to provide remediation advice, creating a vector for indirect instructions. \n
- Ingestion points: The skill ingests user-provided SwiftUI views, data flow code, and Instruments lane screenshots or traces (SKILL.md). \n
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions for the data being analyzed. \n
- Capability inventory: The skill's capabilities are limited to providing architectural advice and code review; it does not contain instructions to write to the file system or perform network operations. \n
- Sanitization: No explicit sanitization or filtering of user-supplied code snippets is mentioned.
Audit Metadata