{"answers":{"affected":"It affects 1 product.","exploited":"There is no known exploitation of CVE-2026-15829 in the wild and no public exploit code.","fix":"No fix has been published for CVE-2026-15829 yet. Limit exposure of the affected software until one is available.","what":"CVE-2026-15829 is a high-severity SQL injection vulnerability in MCP Toolbox for Databases (googleapis/mcp-toolbox), published on 21 Jul 2026. Any signed-in user can exploit it over the network, with no action from the victim."},"fix_prompt":"Check this codebase for CVE-2026-15829 and fix it if it is affected.\n\nWhat it is: CVE-2026-15829 is a high-severity SQL injection vulnerability in MCP Toolbox for Databases (googleapis/mcp-toolbox), published on 21 Jul 2026. Any signed-in user can exploit it over the network, with no action from the victim.\nExploitation: There is no known exploitation of CVE-2026-15829 in the wild and no public exploit code.\n\nAffected product: MCP Toolbox for Databases (googleapis/mcp-toolbox). No package-level version data is available, so check the vendor advisory linked from the reference page.\n\nTask:\n1. Search the dependency manifests and lockfiles (for example package.json, package-lock.json, requirements.txt, poetry.lock, uv.lock, pom.xml, build.gradle, go.mod, Cargo.lock, Gemfile.lock) and any Dockerfiles for the affected packages, including transitive dependencies.\n2. If an affected version is in use, upgrade it to the fixed version for its release line with the project's package manager, so the lockfile is regenerated. Prefer the smallest upgrade that fixes it.\n3. If there is no fix, or the upgrade would break the build, do not guess: explain the risk and the safest workaround instead.\n4. Run the tests and summarise what changed and why.\n5. If nothing in the project is affected, say so and change nothing.\n\nReference: https://insights.sbomify.com/CVE-2026-15829/ (Markdown: https://insights.sbomify.com/CVE-2026-15829/index.md)","id":"CVE-2026-15829","markdown":"https://insights.sbomify.com/CVE-2026-15829/index.md","name":"CVE-2026-15829","record":{"aliases":["GHSA-wvx3-gvxv-cmxc"],"analysis":{"component_type":"server_software","fix_type":"patch","impacts":["data_read","security_bypass"],"network_reachable":"yes","non_default_config":false,"product_category":"MCP Toolbox for Databases","requires_auth":"low_privilege","summary":"Attackers can inject SQL into BigQuery forecasting tools to bypass dataset restrictions and read arbitrary tables.","user_interaction":"not_required","vuln_class":"sql_injection"},"analysis_generated_by":"qwen3.8-flash-next","assigner":"Google","cpe":[{"product":"mcp_toolbox_for_databases","vendor":"google"}],"cvss":{"score":8.6,"severity":"high","source":"cna","vector":"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","version":"4.0"},"cwes":[{"id":"CWE-89","name":"Improper Neutralization of Special Elements used in an SQL Command"},{"id":"CWE-863","name":"Incorrect Authorization"}],"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.\n\nThe 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.\n\nAn 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.","ecosystems":[],"exploits":{"exploitdb":0,"first_seen":null,"github_poc":0,"max_poc_stars":null,"metasploit":0,"nuclei":0,"refs":[],"tier":"none_known"},"has_fix":false,"headline":"SQL Injection and Security Boundary Bypass in googleapis/mcp-toolbox","id":"CVE-2026-15829","indexable":true,"kev":null,"kind":"cve","links":{"ecosystem":null,"product":null,"products":[],"type":"sql_injection","year":"2026"},"n_packages":0,"n_references":1,"next":{"headline":"Potential denial-of-service vulnerability via nested geometry collections","id":"CVE-2026-15830"},"packages":[],"prev":{"headline":"Missing authorization in GutenKit – Page Builder Blocks, Patterns, and Templates for Gutenberg Block Editor","id":"CVE-2026-15827"},"products":["MCP Toolbox for Databases (googleapis/mcp-toolbox)"],"published":"2026-07-21","related":[{"cvss_score":9.3,"headline":"Path Traversal in googleapis/mcp-toolbox HTTP Tool URL Builder","id":"CVE-2026-11720","kev_date_added":null,"published":"2026-06-29"},{"cvss_score":9.3,"headline":"googleapis/mcp-toolbox: authentication bypass vulnerability in the generic opaque token validation path (validateOpaqueToken)","id":"CVE-2026-11717","kev_date_added":null,"published":"2026-06-18"},{"cvss_score":9.3,"headline":"googleapis/mcp-toolbox: authentication bypass vulnerability in the generic opaque token validation path (validateOpaqueToken)","id":"CVE-2026-11718","kev_date_added":null,"published":"2026-06-18"},{"cvss_score":8.6,"headline":"MCP Toolbox for Databases: authenticated authorization bypass","id":"CVE-2026-11719","kev_date_added":null,"published":"2026-06-18"},{"cvss_score":8.1,"headline":"Authorization Bypass in MCP Toolbox Legacy HTTP Endpoints","id":"CVE-2026-14537","kev_date_added":null,"published":"2026-07-31"},{"cvss_score":8,"headline":"Server-Side Request Forgery via Unrestricted HTTP Redirection in MCP Toolbox","id":"CVE-2026-14540","kev_date_added":null,"published":"2026-07-31"}],"sources":[{"class":"attribution","licence":"CVE Terms of Use (MITRE)","name":"CVE List","prefix":"CVE"},{"class":"attribution","licence":"US public information, NVD API terms","name":"NVD"},{"class":"attribution","licence":"CWE Terms of Use","name":"CWE (MITRE)"},{"class":"attribution","licence":"FIRST CVSS licence","name":"CVSS (FIRST)"}],"ssvc":{"automatable":"no","exploitation":"none","technical_impact":"total"},"state":"PUBLISHED","updated":"2026-07-22","vendors":["Google"]},"summary":"Attackers can inject SQL into BigQuery forecasting tools to bypass dataset restrictions and read arbitrary tables.","url":"https://insights.sbomify.com/CVE-2026-15829/"}