compose-adaptive

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists of legitimate technical documentation and code snippets for Android development. The instructions guide the AI agent through best practices for implementing adaptive layouts with modern Jetpack Compose APIs.
  • [EXTERNAL_DOWNLOADS]: The skill references official Android developer documentation (developer.android.com) and a public GitHub repository from the Android organization (github.com/android). These references are used for providing additional technical context and sample code recipes for developers.
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to analyze the user's codebase to identify UI patterns (e.g., list-detail relationships). While this involves processing external data, the instructions are scoped to standard development tasks and do not introduce unique vulnerability surfaces beyond the typical operation of a coding assistant.
  • Ingestion points: User project source code and layout files.
  • Boundary markers: None explicitly defined in the instructions.
  • Capability inventory: Code analysis and generation based on user project structure.
  • Sanitization: None specified; the skill relies on the agent's inherent safety guardrails when processing project data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 01:14 PM
Security Audit — agent-trust-hub — compose-adaptive