databricks-execution-compute

Pass

Audited by Gen Agent Trust Hub on Jun 26, 2026

Risk Level: SAFECOMMAND_EXECUTIONREMOTE_CODE_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the databricks CLI to perform various workspace and compute management tasks, which involves the execution of shell commands on the host system.
  • [REMOTE_CODE_EXECUTION]: The skill's primary functionality is to enable the execution of Python, SQL, Scala, and R code on remote Databricks compute resources via the jobs and command execution APIs.
  • [PROMPT_INJECTION]: The skill ingests data from remote execution outputs (e.g., notebook results). This establishes an indirect prompt injection surface where untrusted data returned from the Databricks platform could potentially contain instructions designed to influence the agent's logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 26, 2026, 01:24 PM
Security Audit — agent-trust-hub — databricks-execution-compute