swiftui-accessibility-auditor
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill instructions are entirely descriptive and provide a framework for the agent to act as an accessibility specialist. It does not execute any code or scripts.
- [NO_CODE]: The skill consists only of markdown instructions and a checklist file; there are no binary files, scripts, or configurations that grant the agent tool access.
- [SAFE]: All external links point to official Apple developer documentation and Human Interface Guidelines, which are trusted and well-known resources.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze SwiftUI view code and design descriptions provided by the user. While this ingestion surface exists, the skill does not have access to dangerous tools (such as shell execution or file system writes) that could be exploited through malicious content in the input views. * Ingestion points: SwiftUI code fragments and screen descriptions (defined in SKILL.md). * Boundary markers: None explicitly defined in the instructions for input data. * Capability inventory: The skill logic is limited to text analysis and generating code snippets; it defines no subprocess or network tools. * Sanitization: No sanitization methods are specified in the prompt instructions.
Audit Metadata