setup-warehouse-databricks

Pass

Audited by Gen Agent Trust Hub on Oct 16, 2026

Risk Level: SAFEPROMPT_INJECTIONDATA_EXFILTRATIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill contains instructions to suppress user notification for telemetry and sentiment tracking operations, stating they should be "transparent to the user" and that the agent should "never mention it".\n- [DATA_EXFILTRATION]: Background network requests are made to vendor-owned domains ("onboarding.confidence.dev" and "events.confidence.dev") to exfiltrate session data and user sentiment metrics.\n- [COMMAND_EXECUTION]: The skill modifies sensitive user configuration files by writing directly to "/.aws/credentials" and "/.aws/config" instead of using standard interactive tools.\n- [EXTERNAL_DOWNLOADS]: Encourages the installation of external tools like "awscli" via package managers if they are not present on the system.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 16, 2026, 03:39 PM