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.
Analysis
Analysis and contextual insights are available on OpenCVE Cloud.
Default status is the baseline for the product, each version can override it (e.g. patched versions marked unaffected).
| Vendor | Product | Default status | Versions | ||||||
|---|---|---|---|---|---|---|---|---|---|
| MCP Toolbox for Databases (googleapis/mcp-toolbox) | unaffected |
|
No data.
No data.
No data available yet.
No vendor fix or workaround currently provided.
Additional remediation guidance may be available on OpenCVE Cloud.
Tracking
Sign in to view the affected projects.
No advisories yet.
| Link | Providers |
|---|---|
| https://github.com/googleapis/mcp-toolbox/pull/3324 |
|
Tue, 21 Jul 2026 17:00:00 +0000
| Type | Values Removed | Values Added |
|---|---|---|
| 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. | |
| Title | SQL Injection and Security Boundary Bypass in googleapis/mcp-toolbox | |
| Weaknesses | CWE-863 CWE-89 |
|
| References |
| |
| Metrics |
cvssV4_0
|
Subscriptions
No data.
MITRE
Status: PUBLISHED
Assigner: Google
Published:
Updated: 2026-07-21T16:39:54.968Z
Reserved: 2026-07-15T15:00:56.723Z
Link: CVE-2026-15829
Vulnrichment
No data.
NVD
No data.
Redhat
No data.
OpenCVE Enrichment
No data.