PatchSiren cyber security CVE debrief
CVE-2026-15829 Google CVE debrief
CVE-2026-15829 is a SQL injection and security boundary bypass vulnerability in the prebuilt BigQuery forecasting tool (bigquery-forecast) of googleapis/mcp-toolbox. The tool accepts client-controlled parameters as plain strings and interpolates them unescaped into a generated AI.FORECAST table-valued SELECT statement. This allows an unauthorized user to bypass the operator-configured allowedDatasets boundary and read arbitrary BigQuery tables.
- Vendor
- Product
- MCP Toolbox for Databases (googleapis/mcp-toolbox)
- CVSS
- HIGH 8.6
- CISA KEV
- Not listed in stored evidence
- Original CVE published
- 2026-07-21
- Original CVE updated
- 2026-07-22
- Advisory published
- 2026-07-21
- Advisory updated
- 2026-07-22
Who should care
Users of googleapis/mcp-toolbox, particularly those who utilize the prebuilt BigQuery forecasting tool, should be aware of this vulnerability and take steps to mitigate it. This includes operators managing BigQuery datasets, platform administrators responsible for security configurations, vulnerability management teams assessing risk, and security teams monitoring for potential exploitation.
Technical summary
The prebuilt BigQuery forecasting tool (bigquery-forecast) of googleapis/mcp-toolbox is vulnerable to SQL injection (CWE-89) and security boundary bypass (CWE-863). 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.
Defensive priority
High
Recommended defensive actions
- Review and update the prebuilt BigQuery forecasting tool to properly validate and sanitize client-controlled parameters.
- Implement additional security measures to restrict query execution and prevent unauthorized access to BigQuery tables.
- Monitor for suspicious activity and update the tool with the latest security patches.
- Perform a thorough review of the current BigQuery forecasting tool deployment to identify potential exposure.
- Inventory assets that utilize the prebuilt BigQuery forecasting tool and prioritize remediation efforts.
- Establish a rollback plan in case of issues with applying security patches.
- Track the status of security patches and updates for the BigQuery forecasting tool.
Evidence notes
The CVE record was published on 2026-07-21T17:17:05.350Z and was last modified on 2026-07-22T19:16:55.480Z. The NVD entry is currently Awaiting Analysis. Evidence is limited to CVE and NVD entries. Defenders should verify BigQuery forecasting tool usage, review allowedDatasets configurations, and monitor for suspicious query activity.
Official resources
-
CVE-2026-15829 CVE record
CVE.org
-
CVE-2026-15829 NVD detail
NVD
-
Source item URL
nvd_modified
- Source reference
AI-assisted PatchSiren debrief based on the supplied source corpus. The CVE record was published on 2026-07-21T17:17:05.350Z and has not been modified since then. The NVD entry is currently Awaiting Analysis.