write-script-bigquery

Pass

Audited by Gen Agent Trust Hub on Aug 18, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the wmill CLI tool to perform actions such as script preview, script run, and generate-metadata. These commands are standard operations within the Windmill developer ecosystem for managing and testing scripts.
  • [DYNAMIC_EXECUTION]: The agent generates SQL and script code which is then executed locally via the wmill CLI tool. This is expected behavior for a developer-oriented skill and follows standard platform workflows.
  • [DATA_EXPOSURE]: The skill describes functionality to read from and write to S3 buckets using the (s3object) parameter type and -- s3 streaming directives, which are documented features of the Windmill platform for BigQuery.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data via S3 object parameters and SQL query results. (1) Ingestion points: S3 files and BigQuery result sets. (2) Boundary markers: Utilizes standard SQL parameter syntax (e.g., @name) to delimit data from query logic. (3) Capability inventory: Access to the wmill CLI for script execution and synchronization. (4) Sanitization: Relies on native database parameterization and platform-level decoding of S3 objects.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 18, 2026, 04:44 AM
Security Audit — agent-trust-hub — write-script-bigquery