bigquery-analyst
Warn
Audited by Snyk on May 6, 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). The SKILL.md "Exogenous Context Injection (Advanced)" step explicitly instructs the agent to cross-reference internal data with public BigQuery datasets (e.g., gdelt-bq.gdeltv2 and bigquery-public-data.google_trends), meaning the agent will fetch and interpret open, third-party data that can materially influence analysis.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata