performance-audit
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill content is strictly instructional and focuses on legitimate iOS development practices for performance optimization. It includes common code patterns and their optimized equivalents.
- [INDIRECT_PROMPT_INJECTION]: The skill establishes a data ingestion surface by requesting user-supplied SwiftUI code and performance symptoms in SKILL.md. There are no explicit boundary markers or sanitization procedures for this external content. However, the capability inventory is restricted to diagnostic analysis and providing instructions for manual developer tools (e.g., xcodebuild, Instruments), which does not present an exploitable autonomous attack surface.
Audit Metadata