bigquery

Warn

Audited by Snyk on Feb 17, 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 explicitly ingests arbitrary third-party data (e.g., "curl -s https://api.example.com/export.csv | bigquery tables insert ..." and creating external tables from gs:// URIs or streaming stdin), so the agent can read and act on untrusted/public content as part of its workflow.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 17, 2026, 01:06 PM