SQL Injection and Security Boundary Bypass in googleapis/mcp-toolbox
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.
- Products
- Not specified
- Affected versions
- Not specified
- Fixed versions
- Not specified
- CVEs
- CVE-2026-15829
- Confirmed fixed CVEs
- Not specified
- Updated in this feed
- 3 Nov 2026, 15:20 UTC · Revision 1
Source evidence
SQL Injection and Security Boundary Bypass in googleapis/mcp-toolbox
core-osv · Original sourcePublished 21 Jul 2026, 16:39 UTC
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.
osv:CVE-2026-15829
Complete source record
{
"id": "9cbe789d6fd14f77bc4edbf381eeb88cc08cca83495d5ce677e5987d14d2ab2c",
"url": "https://osv.dev/vulnerability/CVE-2026-15829",
"method": "structured",
"payload": {
"kind": "advisory",
"title": "SQL Injection and Security Boundary Bypass in googleapis/mcp-toolbox",
"summary": "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.",
"evidence": "osv:CVE-2026-15829",
"products": [],
"severity": "high",
"structured": {
"id": "CVE-2026-15829",
"aliases": [
"CVE-2026-15829"
],
"metrics": [
{
"type": "CVSS_V4",
"score": "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"
}
],
"affected": [
{
"ranges": [
{
"repo": "https://github.com/googleapis/mcp-toolbox",
"type": "GIT",
"events": [
{
"introduced": "1a6dfe8d37d0f42fb3fd3f75c50988534dbc1b85"
},
{
"last_affected": "b0010060a939455d91e4f8ba62dc3e72b1892469"
}
],
"database_specific": {
"extracted_events": [
{
"range": [
{
"introduced": "0.13.0"
},
{
"last_affected": "1.3.0"
}
],
"source": "AFFECTED_FIELD",
"strategy": "StandardRange"
},
{
"cpe": "cpe:2.3:a:google:mcp_toolbox_for_databases:*:*:*:*:*:*:*:*",
"range": [
{
"introduced": "0.13.0"
},
{
"last_affected": "1.3.0"
}
],
"source": "CPE_RANGE"
}
]
}
}
],
"versions": [
"v1.3.0",
"v1.2.0",
"v1.1.0",
"v1.0.0",
"v0.32.0",
"v0.31.0",
"v0.30.0",
"v0.29.0",
"v0.28.0",
"v0.27.0",
"v0.26.0",
"v0.25.0",
"v0.24.0",
"v0.23.0",
"v0.22.0",
"v0.21.0",
"v0.20.0",
"v0.19.1",
"v0.18.0",
"v0.17.0",
"v0.16.0",
"v0.15.0",
"v0.14.0",
"v0.13.0"
],
"database_specific": {
"source": "https://storage.googleapis.com/cve-osv-conversion/osv-output/CVE-2026-15829.json"
}
}
],
"modified": "2026-10-28T02:30:29.716630379Z",
"provider": "osv",
"references": [
"https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/15xxx/CVE-2026-15829.json",
"https://nvd.nist.gov/vuln/detail/CVE-2026-15829",
"https://github.com/googleapis/mcp-toolbox/pull/3324"
],
"provider_metadata": {
"cwe_ids": [
"CWE-863",
"CWE-89"
],
"cna_assigner": "Google",
"osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/15xxx/CVE-2026-15829.json"
}
},
"related_cves": [
{
"value": "CVE-2026-15829",
"evidence": "/id"
}
],
"security_relevant": true,
"severity_evidence": "/severity/0/score"
},
"source_id": "core-osv",
"document_id": 496768,
"published_at": "2026-07-21T16:39:54.968+00:00"
}