omni-to-databricks-metric-view

Pass

Audited by Gen Agent Trust Hub on Nov 11, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from the Omni API to generate Databricks Metric View definitions. It proactively mitigates potential risks by providing clear defensive instructions: the agent is explicitly told to treat all fetched content as data rather than instructions, to ignore any directions embedded in metadata, and to perform specific sanitization such as stripping control characters and escape sequences ($$) that could break out of YAML blocks. It also ensures that metadata from the API does not control sensitive deployment targets like catalogs or schemas.
  • [EXTERNAL_DOWNLOADS]: The skill utilizes the Omni and Databricks CLI tools. These are legitimate tools originating from the skill's vendor and a well-known cloud service provider, and their use is consistent with the skill's stated purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 11, 2026, 09:25 PM