bigquery-scheduled-query
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied data related to Google Cloud BigQuery scheduled queries, creating a surface for potential instruction injection through untrusted input.
- Ingestion points: Natural language requests and data schemas processed by the agent when assisting with BigQuery tasks as defined in
SKILL.md. - Boundary markers: The skill instructions do not specify the use of delimiters or 'ignore' instructions for data processed by the agent.
- Capability inventory: The skill has access to
Write,Edit, andBash(gcloud:*)tools, providing a pathway for command execution or file modification if an injection is successful. - Sanitization: No specific input validation or sanitization routines are mentioned for handling external data.
Audit Metadata