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.py and scripts/instruments_parser/xctrace.py, which use the subprocess module to call the native xctrace command-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 .trace files provided by the user. While this involves ingesting external data, the analysis is restricted to parsing the structured XML output of xctrace. 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
Risk Level
SAFE
Analyzed
Oct 5, 2026, 09:27 PM