mobile-instinct-v1
Pass
Audited by Gen Agent Trust Hub on Feb 20, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE] (SAFE): The provided skill file contains only markdown documentation describing a mobile development assistant. No executable scripts (.py, .js, .sh), binaries, or configuration files defining logic were included for analysis.
- [INDIRECT_PROMPT_INJECTION] (SAFE): The skill describes a mechanism for capturing patterns from user-written code (.kt files, ViewModels). While this represents a data ingestion surface, there are no instructions or tools provided that could be manipulated to perform unauthorized actions.
- Ingestion points: Analyzes user-created .kt files and code blocks during development.
- Boundary markers: None mentioned.
- Capability inventory: No subprocess calls, network operations, or file-writing capabilities are defined in the provided file.
- Sanitization: Not applicable as no processing logic is provided.
Audit Metadata