PatchSiren

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
Google
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.

Sources and references

Verified primary and authoritative sources

  • CVE-2026-15829 CVE Program record

    Publisher, destination, and source semantics verified

    URL: https://www.cve.org/CVERecord?id=CVE-2026-15829

    CVE Program - Official CVE Program record with source-provided CVE metadata.

  • CVE-2026-15829 NVD vulnerability detail

    Publisher, destination, and source semantics verified

    URL: https://nvd.nist.gov/vuln/detail/CVE-2026-15829

    NIST National Vulnerability Database - Official NIST NVD detail page and source-specific vulnerability assessment.

Supplemental references

Methodology and review provenance

AI-assisted synthesis based on stored public vulnerability evidence. System validation, approval state, and publication status do not by themselves establish human review of this revision. PatchSiren helps prioritize defensive review and does not prove exposure or remediation on any system.