swiftui-ui-patterns

Pass

Audited by Gen Agent Trust Hub on Oct 5, 2026

Risk Level: SAFEDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The file 'references/scroll-reveal.md' contains hardcoded absolute local file paths (e.g., '/Users/dimillian/Documents/Dev/Pool/pool-ios/Pool/Sources/Features/Tile/Detail/TileDetailView.swift') which reveal the author's local system structure and development environment handle.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided UI requirements and existing code for refactoring, creating a surface for indirect prompt injection.\n
  • Ingestion points: User-provided descriptions and SwiftUI code snippets for analysis or refactoring, as described in 'SKILL.md'.\n
  • Boundary markers: The skill lacks explicit instructions or delimiters to distinguish user-supplied code from internal agent instructions.\n
  • Capability inventory: The skill leverages the agent's generative capabilities to create or modify code based on user inputs.\n
  • Sanitization: There are no instructions for sanitizing or escaping user content before it is processed by the agent to generate new UI code.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 5, 2026, 09:27 PM