screen-ux-audit

Pass

Audited by Gen Agent Trust Hub on Jul 6, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references external companion skills from public repositories (e.g., skydoves/android-testing-skills, aldefy/compose-skill) to provide specialized guidance for Android development. These are standard references within a developer tools ecosystem.
  • [COMMAND_EXECUTION]: Contains instructions to run standard Android development validation commands using the Gradle wrapper (e.g., ./gradlew test, ./gradlew lint). These commands are typical for the described UX audit workflow to ensure code stability before making design changes.
  • [PROMPT_INJECTION]: The skill is designed to process external code files (e.g., *Screen.kt, *ViewModel.kt). This presents an indirect prompt injection surface where maliciously crafted content in the files being audited could attempt to influence the agent's output. However, the skill includes a specific rubric and structured report template to help ground the agent's findings in observable evidence.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 6, 2026, 12:30 PM
Security Audit — agent-trust-hub — screen-ux-audit