discovering-gcp-data-assets
Warn
Audited by Snyk on Apr 28, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). This skill explicitly instructs (Step 1: "Public Datasets (Direct Inspection)") to directly inspect public BigQuery datasets (bigquery-public-data) using the bq CLI or BigQuery tools, which causes the agent to fetch and interpret open/public dataset content that could contain untrusted, user-provided material.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata