inputs
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The content is purely educational and instructional, providing standard code snippets for handling hardware events in a mobile application. No malicious patterns, obfuscation, or unauthorized network operations were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill outlines a data ingestion surface for hardware input events from connected glasses. Evidence analysis: 1. Ingestion points:
inputs.events.collectinSKILL.md. 2. Boundary markers: Absent (standard programmatic event handling). 3. Capability inventory: Local UI actions such as focus movement, view dismissal, and button handling. 4. Sanitization: Events are processed as strongly-typed Kotlin objects (InputEvent), which prevents arbitrary string injection. The surface is consistent with the primary purpose of the skill and poses no risk.
Audit Metadata