bigquery-bigframes
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of data from external BigQuery tables, which could potentially contain malicious instructions.
- Ingestion points: Data ingestion is performed via
bpd.read_gbq()inreferences/linear_regression.mdandreferences/logistic_regression.md. - Boundary markers: Absent. The skill does not provide instructions to the agent on how to distinguish data from instructions or to treat external data as untrusted.
- Capability inventory: The skill enables the agent to perform data analysis, model training, and predictions within a BigQuery environment.
- Sanitization: Absent. There is no evidence of data validation or sanitization being applied to the ingested content.
Audit Metadata