gcp-bq-data-export

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • Prompt Injection (SAFE): No attempts to override agent instructions or bypass safety guidelines were found. The content is purely instructional.
  • Data Exposure & Exfiltration (SAFE): While the skill describes data movement, it uses generic placeholders like 'gs://bucket/' and 'PROJECT:DATASET.TABLE'. No hardcoded credentials, API keys, or access to sensitive local files were detected.
  • Remote Code Execution (SAFE): The skill provides standard command-line examples for the 'bq' utility and SQL statements. It does not include patterns for downloading or executing external scripts (e.g., curl | bash).
  • Obfuscation (SAFE): All text and code snippets are in plain, human-readable format without any encoding or hidden characters.
  • Privilege Escalation (SAFE): The documentation mentions standard IAM roles for troubleshooting purposes and does not include commands for unauthorized privilege acquisition.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:19 PM