gcp Google Cloud release notes ·

Security Command Center adds malicious skill threat detectors

aisecuritygcpengineergcp-cloud-rungcp-gke
feature

Security Command Center has introduced new threat detectors for GKE, Cloud Run, and Agent Platform that identify the execution or loading of malicious AI agent skills. These detectors are crucial for protecting against sophisticated threats where malicious binaries are disguised as AI capabilities. This feature is now available to users managing these compute services on Google Cloud.

Features (1)
  • Security Command Center

    Security Command Center released new Malicious Skill runtime threat detectors for Google Kubernetes Engine (GKE), Cloud Run, and Agent Platform. These detectors identify when a malicious skill (an AI agent capability) is executed or loaded. A malicious skill is any malicious binary that has been tagged as an LLM skill by Google's threat intelligence. For more information, see the following: Container Threat Detection overview Cloud Run Threat Detection overview Agent Platform overview

Read the original announcement →

https://docs.cloud.google.com/release-notes#August_04_2026

Related releases