android-navigation
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill contains only documentation, code snippets, and evaluation prompts for Android development. No active code, scripts, or network operations are included in the skill body or referenced files.
- [INDIRECT_PROMPT_INJECTION]: The skill defines triggers for Kotlin files (
**/*Screen.kt,**/*Activity.kt,**/NavGraph.kt) inSKILL.md, creating a potential ingestion surface for untrusted data. However, analysis of the skill reveals no capabilities (such as shell execution, network requests, or file modifications) that would allow an injection to perform malicious actions. - Ingestion points: Triggered by user-provided Kotlin source files.
- Boundary markers: None provided in the prompt templates.
- Capability inventory: No subprocess calls, network operations, or file-write capabilities are requested or used.
- Sanitization: Not applicable as no data is processed or outputted through tools.
Audit Metadata