omni-model-builder
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
curlto interact with the Omni REST API for model updates. This is the primary intended function and targets the vendor's own API endpoint (omniapp.co). - [EXTERNAL_DOWNLOADS]: Links provided in the skill point to official documentation and resource pages on verified vendor domains (
omni.coandomniapp.co). - [CREDENTIALS_UNSAFE]: The skill correctly uses placeholders for API keys and recommends using environment variables, avoiding the use of hardcoded credentials.
- [PROMPT_INJECTION]: Included YAML templates contain an
ai_contextfield. This is a legitimate metadata feature of the Omni platform and is used here to provide modeling context rather than to bypass security controls.
Audit Metadata