bigquery-ai-ml
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a reference library for BigQuery AI SQL functions (
AI.FORECAST,AI.CLASSIFY,AI.GENERATE, etc.). It contains no executable scripts or commands beyond illustrative SQL examples. - [SAFE]: No evidence of prompt injection, obfuscation, or unauthorized data access was found. The examples use standard BigQuery public datasets and generic connection placeholders.
- [INDIRECT_PROMPT_INJECTION]: While the skill defines functions that process text data (e.g.,
AI.GENERATE), it does so within the context of structured SQL queries. This is a standard operational surface for data analysis tools and does not introduce novel security vulnerabilities into the agent's environment. - [SAFE]: The skill author ('google-adk') and the content (Google BigQuery documentation) are consistent with legitimate developer resources for the Google Cloud platform.
Audit Metadata