omni-ai-optimizer

Pass

Audited by Gen Agent Trust Hub on Apr 24, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references the official Omni CLI hosted on the vendor's GitHub repository (github.com/exploreomni/cli). This is a known vendor resource used for the intended purpose of the skill.
  • [PROMPT_INJECTION]: The skill is designed to generate ai_context and sample_queries which are instructions that influence the behavior of a downstream AI system. While this constitutes an indirect prompt injection surface, it is the primary, documented purpose of the skill within the Omni platform environment.
  • Ingestion points: The agent processes user requests for model optimization and reads existing model metadata via the CLI.
  • Boundary markers: No explicit delimiters are used for the generated YAML content.
  • Capability inventory: The skill uses omni models yaml-create to write configuration changes to the Omni API.
  • Sanitization: No explicit sanitization of user input is performed before inclusion in the model YAML.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 24, 2026, 11:14 PM