android-jetpack-compose
Pass
Audited by Gen Agent Trust Hub on Aug 6, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is composed entirely of Markdown documentation and instructional Kotlin code snippets. It does not include any scripts, tools, or configuration that would allow for command execution or file system access.
- [EXTERNAL_DOWNLOADS]: The skill contains a link to the official Google 'Now in Android' sample repository on GitHub. This is an industry-standard reference for clean architecture and Compose best practices, and it does not trigger any remote code execution or automated downloads within the agent's environment.
- [INDIRECT_PROMPT_INJECTION]: The skill serves as a template for UI generation, creating a potential surface for indirect prompt injection if an agent uses these patterns to process untrusted user requirements without proper isolation.
- Ingestion points: User-provided UI requirements processed by the agent using this skill (SKILL.md).
- Boundary markers: None present in the instructional text.
- Capability inventory: The skill enables UI code generation and refactoring.
- Sanitization: None provided; the skill relies on the underlying LLM's safety filters.
Audit Metadata