bigquery-ai-ml
Warn
Audited by Snyk on Oct 18, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The skill instructs the agent to write BigQuery SQL queries that process enterprise datasets (such as tables containing user reviews, emails, and support tickets) using AI/ML functions, which exposes the agent to outsider-authored text when analyzing untrusted data tables.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata