Google MCP Toolbox for Databases up to 1.3.0 Forecast fmt.Sprintf data_col/timestamp_col/id_cols sql injection

Summaryinfo

A vulnerability marked as critical has been reported in Google MCP Toolbox for Databases up to 1.3.0. Impacted is the function fmt.Sprintf of the component Forecast. Performing a manipulation of the argument data_col/timestamp_col/id_cols results in sql injection. This vulnerability is cataloged as CVE-2026-15829. It is possible to initiate the attack remotely. There is no exploit available.

Detailsinfo

A vulnerability classified as critical has been found in Google MCP Toolbox for Databases up to 1.3.0. This affects the function fmt.Sprintf of the component Forecast. The manipulation of the argument data_col/timestamp_col/id_cols with an unknown input leads to a sql injection vulnerability. CWE is classifying the issue as 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. This is going to have an impact on confidentiality, integrity, and availability. The summary by CVE is:

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.

It is possible to read the advisory at github.com. This vulnerability is uniquely identified as CVE-2026-15829 since 07/15/2026. The exploitability is told to be easy. It is possible to initiate the attack remotely. Technical details of the vulnerability are known, but there is no available exploit. The pricing for an exploit might be around USD $5k-$25k at the moment (estimation calculated on 07/21/2026). The attack technique deployed by this issue is T1505 according to MITRE ATT&CK.

There is no information about possible countermeasures known. It may be suggested to replace the affected object with an alternative product.

Statistical analysis made it clear that VulDB provides the best quality for vulnerability data.

Productinfo

Type

• Artificial Intelligence Software

Vendor

• Google

Name

• MCP Toolbox for Databases

Version

• 1.0
• 1.1
• 1.2
• 1.3.0

License

• free

Website

• Vendor: https://www.google.com/

CPE 2.3info

• 🔒
• 🔒
• 🔒

CPE 2.2info

• 🔒
• 🔒
• 🔒

CVSSv4info

CVSSv3info

CVSSv2info

Exploitinginfo

Threat Intelligenceinfo

Countermeasuresinfo

Timelineinfo

Sourcesinfo

Entryinfo

Statistical analysis made it clear that VulDB provides the best quality for vulnerability data.

Discussion