bigquery-troubleshooting

Pass

Audited by Gen Agent Trust Hub on Sep 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • Indirect Prompt Injection Surface: The skill is designed to interpret diagnostic symptoms by querying BigQuery telemetry data, such as INFORMATION_SCHEMA views. This creates a surface where external data is ingested into the agent's context.
  • Ingestion points: Tool outputs from BigQuery INFORMATION_SCHEMA and the bq CLI tool (referenced in SKILL.md and various domain reference files).
  • Boundary markers: The instructions do not explicitly define boundary markers or delimiters for data ingested from BigQuery queries.
  • Capability inventory: The skill instructs the agent to use gcloud and bq commands for resource inspection and remediation (e.g., bq update and bq query).
  • Sanitization: There are no explicit instructions for sanitizing or validating telemetry data before it is processed by the agent.
  • External Resource Installation: The skill provides guidance for installing companion tools using npx from a repository hosted by a trusted organization. This uses standard package management workflows to acquire necessary dependencies for the troubleshooting suite.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 28, 2026, 10:01 PM
Security Audit — agent-trust-hub — bigquery-troubleshooting