News
Updates, product notes and practical coverage for AI platforms and operators.
Google Cloud has added automatic security scanning, findings and organisation-policy controls for standalone skills in Agent Registry. The release helps platform teams identify unsafe instructions or resources before an agent uses them, apply least-privilege access and enforce governance consistently across reusable capabilities that may otherwise spread quickly between projects and teams.
AWS has published an open-source HIPAA Assistant that reviews infrastructure-as-code and application code for security-rule gaps while citing each finding to exact regulatory text. The tool can scan CloudFormation and Terraform offline, use Amazon Bedrock for application-code analysis, or expose the same cited checklist through an MCP server. AWS stresses that the proposed rule remains subject to change.
Tamnoon says its Bedrock-based Tami platform reduced critical cloud exposure by more than 90 per cent within 90 days, with no production issues across millions of workloads. Four specialised agents investigate findings, assign conservative safety ratings, prepare rollback-aware remediation plans and generate reviewed code before short-lived credentials execute approved changes.
Orca Security has detailed a production natural-language query agent built on Amazon Bedrock. Discovery AI converts ordinary questions into filters for a 900-model cloud data graph, reducing input tokens by 93 per cent, overall query cost by 90 per cent and end-to-end latency from about 60 seconds to 15 seconds.
Google Cloud has put its CLI behind a managed remote MCP server in public preview, letting Gemini Enterprise and other agents call gcloud and BigQuery commands without installing local binaries. The 30 September announcement emphasises caller-scoped IAM, isolated execution and audit logging. Teams should still govern which commands agents can run and verify preview limitations before production use.