swiftui-expert-skill
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill contains Python scripts, specifically
scripts/record_trace.pyandscripts/instruments_parser/xctrace.py, which use thesubprocessmodule to call the nativexctracecommand-line utility. This execution is confined to recording performance data and exporting it to XML for analysis, which aligns with the skill's stated purpose of profiling SwiftUI applications. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze Instruments
.tracefiles provided by the user. While this involves ingesting external data, the analysis is restricted to parsing the structured XML output ofxctrace. The scripts do not use this data to dynamically generate instructions for the AI agent in a way that would allow for prompt injection.
Audit Metadata