CVE-2026-15829
Received Received - Intake

SQL Injection and Security Bypass in googleapis/mcp-toolbox BigQuery Forecasting Tool

Vulnerability report for CVE-2026-15829, including description, CVSS score, EPSS score, affected products, exploitability, helpful resources, and attack-flow context.

Publication date: 2026-07-21

Last updated on: 2026-07-21

Assigner: Google Inc.

Description

A SQL injection (CWE-89) and security boundary bypass (CWE-863) vulnerability exists in the prebuilt BigQuery forecasting tool (bigquery-forecast) of googleapis/mcp-toolbox. The tool accepts client-controlled parameters (data_col, timestamp_col, and id_cols) as plain strings and interpolates them unescaped via fmt.Sprintf directly into a generated AI.FORECAST table-valued SELECT statement. While MCP Toolbox utilizes an allowedDatasets mechanism to restrict queries, this defense only validates the history_data parameter; the final assembled query is executed without re-validation. An attacker can break out of the string literal fields (such as timestamp_col) to inject a valid multi-statement or cross-dataset query block. This allows an unauthorized user to bypass the operator-configured allowedDatasets boundary and read arbitrary BigQuery tables.

CVSS Scores

EPSS Scores

Probability:
Percentile:

Meta Information

Published
2026-07-21
Last Modified
2026-07-21
Generated
2026-07-21
AI Q&A
2026-07-21
EPSS Evaluated
N/A
NVD
EUVD

Affected Vendors & Products

Showing 2 associated CPEs
Vendor Product Version / Range
googleapis bigquery_forecast *
google cloud_mcp_toolbox 1.4.0

Helpful Resources

Exploitability

CWE
CWE Icon
KEV
KEV Icon
CWE ID Description
CWE-863 The product performs an authorization check when an actor attempts to access a resource or perform an action, but it does not correctly perform the check.
CWE-89 The product constructs all or part of an SQL command using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify the intended SQL command when it is sent to a downstream component. Without sufficient removal or quoting of SQL syntax in user-controllable inputs, the generated SQL query can cause those inputs to be interpreted as SQL instead of ordinary user data.

Attack-Flow Graph

AI Quick Actions

Instant insights powered by AI
Executive Summary

This vulnerability is a SQL injection (CWE-89) and security boundary bypass (CWE-863) in the BigQuery forecasting tool of googleapis/mcp-toolbox. The tool improperly handles client-controlled parameters like data_col, timestamp_col, and id_cols by directly inserting them into a generated SQL query without proper escaping. This allows attackers to inject malicious SQL code to bypass dataset restrictions and access unauthorized BigQuery tables.

Detection Guidance

To detect this vulnerability, inspect the BigQuery forecasting tool (bigquery-forecast) in your googleapis/mcp-toolbox deployment for unescaped parameter interpolation in SQL queries. Check if client-controlled parameters like data_col, timestamp_col, and id_cols are directly inserted into fmt.Sprintf without validation. Review logs for suspicious queries bypassing allowedDatasets restrictions.

Impact Analysis

If you use the affected BigQuery forecasting tool, an attacker could exploit this to read sensitive data from BigQuery tables they should not have access to. This could lead to data breaches, unauthorized data exposure, or further lateral movement within your cloud environment depending on the permissions of the compromised account.

Compliance Impact

This vulnerability could lead to unauthorized access to personal or sensitive data, violating GDPR's data protection principles and HIPAA's security requirements for protected health information. Non-compliance may result in legal penalties, fines, or reputational damage due to data exposure.

Mitigation Strategies

Update to release 1.4.0 or later of googleapis/mcp-toolbox to apply the fix. Ensure input validation wraps query parameters in single quotes and performs dry-run validation of assembled SQL queries. Monitor BigQuery access logs for unauthorized dataset queries and restrict MCP Toolbox permissions to least privilege.

Chat Assistant

Ask questions about this CVE
Hi! I’m here to help you understand CVE-2026-15829. Ask me anything about the vulnerability, its impact, or mitigation strategies.
0/70

EPSS Chart