Google BigQuery

AdvisoryAudited by Static analysis on Apr 30, 2026.

Overview

No suspicious patterns detected.

Findings (0)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

Anyone installing the skill should understand that BigQuery access is mediated through Maton and may allow querying or managing data available to the connected Google account.

Why it was flagged

The skill relies on Maton-managed OAuth to act against the user's Google BigQuery account, which is expected for the integration but grants delegated account access.

Skill content
Maton proxies requests to `bigquery.googleapis.com` and automatically injects your OAuth token.
Recommendation

Use a dedicated or least-privileged Google account/connection where possible, and verify the connected project and account before running requests.

What this means

Incorrect or unintended queries and management actions could expose, change, or delete BigQuery resources, or incur query costs.

Why it was flagged

The documented capability includes broad BigQuery operations that can affect datasets, tables, and jobs; this is purpose-aligned, but it is high-impact authority.

Skill content
Run SQL queries, manage datasets and tables, and analyze data at scale.
Recommendation

Confirm project IDs, dataset/table names, and SQL text before execution; require explicit approval for any write, delete, DDL, or DML operation.

What this means

Queries, request metadata, and BigQuery responses may pass through the Maton API gateway as part of normal operation.

Why it was flagged

Requests are routed through a third-party gateway before reaching Google BigQuery; this is disclosed and central to the managed OAuth design.

Skill content
Base URL: `https://api.maton.ai/google-bigquery/bigquery/v2/{resource-path}`
Recommendation

Review Maton's terms and data-handling practices before connecting sensitive BigQuery projects, and avoid sending data beyond what is needed for the task.