swiftui-pro
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze and review user-provided Swift and SwiftUI source code, which serves as a potential vector for indirect instructions.
- Ingestion points: User-provided Swift code snippets and project files submitted for review.
- Boundary markers: The skill includes a defined output format that organizes findings by file and line number, which helps maintain the agent's focus on the review task.
- Capability inventory: The skill focuses on code analysis and reporting. The provided files do not include definitions for tools that could perform destructive actions like network exfiltration or file system modifications.
- Sanitization: The skill relies on the underlying model's safety guardrails, as there are no explicit sanitization or escaping instructions provided for the input code.
- [SAFE]: The skill references external documentation and supplementary agent skills hosted on GitHub.
- Evidence: The skill includes links to other relevant agent skills on GitHub (e.g.,
github.com/twostraws/swiftdata-agent-skill). These links point to the official repositories of the stated author (Paul Hudson) and are used to provide additional context for specific topics like SwiftData or Concurrency.
Audit Metadata