android-architecture
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of documentation and design patterns for Android development using Compose, Hilt, and Clean Architecture. No executable scripts or malicious patterns were identified.
- [INDIRECT_PROMPT_INJECTION]: The skill identifies and provides mitigation guidance for untrusted data ingestion points. 1. Ingestion points: Deep link intents (navigation-deep-links.md) and WebView content (webview-surface.md). 2. Boundary markers: Guidance on mapping DTOs to UI display models to separate layers. 3. Capability inventory: The skill contains no executable tools or commands. 4. Sanitization: Mandatory host/scheme validation for deep links and allowlists/JavaScript policies for WebViews are required.
- [NO_CODE]: This skill only contains architectural guidance and references in Markdown format, with no associated code files or scripts.
Audit Metadata