write-script-bigquery

Pass

Audited by Gen Agent Trust Hub on Jun 22, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the wmill CLI tool for script management tasks such as preview, run, sync push, and generate-metadata. These commands are specific to the Windmill platform provided by the author and are used for their intended purpose of local development and workspace deployment.
  • [PROMPT_INJECTION]: The skill includes instructions to the agent on how to handle user requests, emphasizing the use of script preview over sync push to avoid accidental overwrites of workspace code. These are legitimate operational guidelines and do not attempt to bypass safety filters.
  • [EXTERNAL_DOWNLOADS]: The skill mentions that wmill generate-metadata may re-resolve dependencies, which is standard behavior for dependency management tools when updating lock files.
  • [DATA_EXFILTRATION]: While the skill describes streaming BigQuery results to S3, this is presented as a built-in feature of the Windmill platform for handling large datasets and does not involve unauthorized data movement.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 22, 2026, 08:36 AM
Security Audit — agent-trust-hub — write-script-bigquery