swiftui-performance-audit
Pass
Audited by Gen Agent Trust Hub on Jul 31, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill defines a diagnostic workflow using instructional markdown references. It contains no executable scripts, remote dependencies, or requests for sensitive information.
- [PROMPT_INJECTION]: The skill processes user-supplied SwiftUI code and Instruments trace data (SKILL.md, Section 1), which creates a surface for indirect prompt injection. This risk is minimized as the skill is restricted to analysis tasks and lacks high-privilege capabilities such as shell execution or file-system writing.
- Ingestion points: User-provided code snippets and reproduction steps (SKILL.md).
- Boundary markers: None specified in instructions.
- Capability inventory: Analysis and documentation lookup via web search.
- Sanitization: Not specified.
Audit Metadata