omni-model-explorer

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill interacts with the Omni REST API to fetch metadata about data models, topics, and views. All requests are directed to official vendor domains (omniapp.co and omni.co).
  • [COMMAND_EXECUTION]: Uses standard curl commands to perform HTTP GET requests to the API. The commands are well-formed and used exclusively for data exploration as described.
  • [EXTERNAL_DOWNLOADS]: Fetches model definitions and documentation from the vendor's official resources. These operations are core to the skill's functionality and do not involve executing untrusted code.
  • [PROMPT_INJECTION]: The skill facilitates the ingestion of data model metadata (including AI context and YAML definitions) which is then used by the agent. While this represents a data ingestion surface (SKILL.md, Step 3 and 4), the source is the user's own authenticated Omni environment, and the skill lacks dangerous capabilities like write access or arbitrary execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 09:54 PM