bigquery
Pass
Audited by Gen Agent Trust Hub on Apr 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill makes extensive use of the
bigqueryCLI tool to interact with Google Cloud BigQuery, allowing the agent to perform data manipulation, resource creation, and deletion operations. - [DATA_EXFILTRATION]: Provides instructions for exporting data from BigQuery tables to external Google Cloud Storage (GCS) buckets using the
tables extractcommand. - [PROMPT_INJECTION]: The skill processes external data retrieved from BigQuery queries and files, which serves as a potential surface for indirect prompt injection. \n
- Ingestion points: BigQuery query results and dataset/table metadata retrieved via
bigquery queryandbigquery tables describe. \n - Boundary markers: Not specified; the instructions do not include specific delimiters or warnings to ignore instructions within the processed data. \n
- Capability inventory: The skill utilizes the
bigqueryCLI tool which has the ability to execute SQL, manage cloud resources, and move data. \n - Sanitization: No sanitization or data validation steps are mentioned in the skill instructions.
Audit Metadata