skills/android/skills/adaptive/Gen Agent Trust Hub

adaptive

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides instructions for Android development, focusing on adaptive UI patterns using Jetpack Compose. All code snippets provided are standard Kotlin and Compose implementations for layout management (Grid, FlexBox, NavigationSuiteScaffold) and do not contain any malicious patterns.
  • [EXTERNAL_DOWNLOADS]: The skill references external resources including documentation at developer.android.com and a code repository on GitHub (github.com/android/nav3-recipes). These sources are official developer resources and well-known services associated with the vendor, and are used to provide legitimate reference material for the developer.
  • [COMMAND_EXECUTION]: The instructions involve standard development workflow steps such as running screenshot tests and building the Android application using Gradle. There are no attempts to execute arbitrary or dangerous shell commands.
  • [INDIRECT_PROMPT_INJECTION]: While the skill analyzes and processes the user's application code to suggest UI improvements, it does not possess dangerous capabilities (like network exfiltration or arbitrary code execution) that would make it vulnerable to indirect prompt injection attacks. The suggestions are confined to UI layout and navigation structure.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 07:57 AM
Security Audit — agent-trust-hub — adaptive