Tech Updates — Sep 6 – Sep 12, 2026
· 2 min read
This week's biggest signal is agentic tooling maturing fast across Google Cloud: Gemini Enterprise Agent Platform's Computer Use and Shell sandboxes reached general availability, and Model Context Protocol servers shipped for both API Gateway and IAM. Security teams also have two items to act on — a critical GitLab path-traversal fix and a high-severity Slurm vulnerability affecting Cluster Toolkit. All five domains had material changes this week.
Highlights
- Gemini Enterprise Agent Platform's Computer Use and Shell sandboxes reached general availability, giving agents an isolated browser or Linux shell environment in which to automate tasks. — Gemini Enterprise Agent Platform release notes, Sep 9
- You can now configure API Gateway to act as a remote Model Context Protocol server, in public preview, exposing existing REST APIs to AI agents as tools without changing backend services. — API Gateway release notes, Sep 11
- Appending sqlcommenter tags via the
sql_commenter_enabledparameter when executing SQL queries through a Cloud SQL remote MCP server is temporarily disabled for Cloud SQL for MySQL and PostgreSQL, review before you upgrade any tooling that relies on it. — Cloud SQL release notes, Sep 10 - Google published security bulletin GCP-2026-062 disclosing multiple high-severity Slurm vulnerabilities, including CVE-2026-65107, affecting Cluster Toolkit blueprints, and recommends upgrading to Cluster Toolkit v1.103.0 or later, which updates Slurm to version 25.11.8. — Cluster Toolkit security bulletins, Sep 11
- GitLab shipped a critical patch release (19.3.2, 19.2.6, and 19.1.8) fixing an unauthenticated path-traversal vulnerability in the repository commits API that allowed arbitrary file read, among roughly 17 other security issues, and CISA added it to its Known Exploited Vulnerabilities catalog the next day — teams running self-managed GitLab alongside GCP infrastructure should patch promptly. — GitLab patch release notes, Sep 10