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
Risk Level
SAFE
Analyzed
Feb 20, 2026, 08:25 PM