Quick answer
Direct answer
Risk scores
| CVSS metric | What it means |
|---|---|
| Attack vector (AV:N) | Network: reachable remotely |
| Attack complexity (AC:L) | Low complexity |
| Attack requirements (AT:N) | No attack requirements |
| Privileges required (PR:L) | Low privileges required |
| User interaction (UI:N) | No user interaction |
| Confidentiality (VC:H) | High confidentiality impact |
| Integrity (VI:H) | High integrity impact |
| Availability (VA:N) | No availability impact |
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:N/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
About Google Mcp Toolbox For Databases
CVE-2026-15829 affects Google Mcp Toolbox For Databases, a product from Google. Before acting, confirm where Google Mcp Toolbox For Databases runs in your estate, who owns it and whether it is reachable from the internet, because exposure decides real risk more than the score alone.
What the flaw is
In plain terms: 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.
The weakness class is SQL Injection. Untrusted input changes the meaning of a database query.
Based on its CVSS vector, the flaw can be reached over the network, needs some level of access, and needs no user interaction. Apply the vendor fix and confirm exposure on internet facing and business critical assets first.
Affected versions and timeline
| Field | Detail |
|---|---|
| Product | Google Mcp Toolbox For Databases |
| Affected versions | Mcp Toolbox For Databases from 0.13.0 up to and including 1.3.0 |
| Published | Jul 21, 2026 |
| Last modified | Sep 22, 2026 |
| Added to CISA KEV | Not listed |
| Assigning CNA | cve-coordination@google.com |
How to detect it
- Inventory every instance of Google Mcp Toolbox For Databases and record the running version against the affected range above.
- Check external attack surface scans for internet facing instances of the component.
- Review logs on affected systems for unusual requests, errors or new processes around the vulnerable function.
- Confirm with an authenticated vulnerability scan once your scanner has a check for this CVE.
How to fix it
- Apply the fixed version of Google Mcp Toolbox For Databases named in the vendor advisory.
- If patching must wait, restrict network access to the affected service and put it behind authentication or a web application firewall rule.
- Rescan after the change to prove the exposure is gone, then close the ticket.
CTEM action plan
| CTEM stage | What to do for this CVE |
|---|---|
| Scope | Add every business service that depends on Google Mcp Toolbox For Databases to the current CTEM cycle. |
| Discover | Find all instances, including shadow and cloud deployments, and record versions and exposure. |
| Prioritize | Rank using EPSS and CVSS together with asset exposure and business impact. |
| Validate | Confirm the flaw is reachable and exploitable in your environment and that compensating controls work. |
| Mobilize | Assign the fix to the asset owner with a due date matched to the priority, then verify closure. |
CWE References
- CWE-89: SQL Injection More CVEs with this weakness
- CWE-863: Incorrect Authorization More CVEs with this weakness
Technical References
Frequently asked questions
Related CVEs
Incorrect authorization in Mojo in Google Chrome on on Windows prior to 155.0.8059.79 allowed a local attacker to potentially execute arbitrary code outside the sandbox via a local program. (Chromium security severity: High)
Information leak in Permissions in Google Chrome prior to 155.0.8059.39 allowed a remote attacker to bypass site isolation via a crafted HTML page. (Chromium security severity: Low)
Confused deputy in WebAPKs in Google Chrome on on Android prior to 155.0.8059.39 allowed a remote attacker leveraging social engineering to bypass web origin policy via a crafted HTML page. (Chromium security severity: Low)
Incorrect authorization in Actor in Google Chrome on on Android prior to 155.0.8059.39 allowed a remote attacker who had compromised the renderer process to potentially bypass site isolation via a crafted HTML page. (Chromium security severity: Low)
Missing authorization in FileSystem in Google Chrome prior to 155.0.8059.39 allowed a remote attacker who had compromised the renderer process to bypass web origin policy via a crafted HTML page. (Chromium security severity: Medium)
Missing authorization in Navigation in Google Chrome on on iOS prior to 155.0.8059.39 allowed a remote attacker to bypass web origin policy into a privileged page via a crafted HTML page. (Chromium security severity: Medium)
Earn your free CTEM certification.
Learn to scope, prioritize, validate and mobilize fixes for CVEs like CVE-2026-15829 with a free CTEM certification.
Beginner / Practitioner / Program Leader
Explore certifications