databricks-workspace-config
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The instructions suggest applying 'MINIMAL pushback' regarding a customer's design choices. Within the context of administrative 'day-2 operations', this is a stylistic guidance for the agent's interaction model rather than an attempt to bypass safety guardrails or ignore system instructions.
- [EXTERNAL_DOWNLOADS]: The skill includes a Terraform configuration example that fetches the deployer's public IP from
https://ifconfig.me. This is a standard practice to ensure the administrator is included in allow-lists, preventing accidental lockout from the workspace API. - [INDIRECT_PROMPT_INJECTION]: The skill provides an interface for managing workspace configurations, policies, and secrets. While this involves handling user-supplied data that could influence downstream systems, the skill mitigates risk by requiring explicit user approval for every 'remote mutation' and implementing human-in-the-loop verification.
Audit Metadata