oxi-e16

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS] (LOW): The skill is distributed via a personal GitHub repository (brentvatne/oxi-e16-configuration) instead of a trusted organization. While common for development, it represents an unverifiable dependency source.
  • [COMMAND_EXECUTION] (LOW): The tool requires running a local Node.js script (generate-scene.js) to convert JSON definitions into MIDI controller files. This is the primary function of the skill but constitutes a local code execution surface.
  • [PROMPT_INJECTION] (LOW): The JSON schema for .oxie16 files defines a 'code' property for custom scripts. This creates a surface for indirect prompt injection where a malicious configuration file could influence agent behavior if the 'code' field is ever interpreted. Ingestion points: User-provided JSON files. Boundary markers: None identified. Capability inventory: Local script execution via Node.js. Sanitization: No sanitization or validation logic is present in the provided schema or metadata.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:44 PM