AI threat findings

Security Command Center has detectors for general AI-related threats and detectors that are designed for AI agents deployed to Vertex AI Agent Engine Runtime.

General AI threats

The following log-based detections are available with Event Threat Detection :

• Initial Access: Dormant Service Account Activity in AI Service
• Persistence: New AI API Method
• Persistence: New Geography for AI Service
• Privilege Escalation: Anomalous Impersonation of Service Account for AI Admin Activity
• Privilege Escalation: Anomalous Multistep Service Account Delegation for AI Admin Activity
• Privilege Escalation: Anomalous Multistep Service Account Delegation for AI Data Access
• Privilege Escalation: Anomalous Service Account Impersonator for AI Admin Activity
• Privilege Escalation: Anomalous Service Account Impersonator for AI Data Access

Threats to agents deployed to Vertex AI Agent Engine Runtime

Preview

This feature is subject to the "Pre-GA Offerings Terms" in the General Service Terms section of the Service Specific Terms . Pre-GA features are available "as is" and might have limited support. For more information, see the launch stage descriptions .

Security Command Center performs runtime and control plane monitoring of AI agents deployed to Vertex AI Agent Engine Runtime.

Runtime finding types

The following runtime detections are available with Agent Platform Threat Detection :

• Command and Control: Steganography Tool Detected
• Credential Access: Find Google Cloud Credentials
• Credential Access: GPG Key Reconnaissance
• Credential Access: Search Private Keys or Passwords
• Defense Evasion: Base64 ELF File Command Line
• Defense Evasion: Base64 Encoded Python Script Executed
• Defense Evasion: Base64 Encoded Shell Script Executed
• Defense Evasion: Launch Code Compiler Tool In Container
• Execution: Added Malicious Binary Executed
• Execution: Added Malicious Library Loaded
• Execution: Built in Malicious Binary Executed
• Execution: Container Escape
• Execution: Fileless Execution in /memfd:
• Execution: Kubernetes Attack Tool Execution
• Execution: Local Reconnaissance Tool Execution
• Execution: Malicious Python Executed
• Execution: Modified Malicious Binary Executed
• Execution: Modified Malicious Library Loaded
• Execution: Netcat Remote Code Execution in Container
• Execution: Possible Arbitrary Command Execution through CUPS (CVE-2024-47177)
• Execution: Possible Remote Command Execution Detected
• Execution: Program Run with Disallowed HTTP Proxy Env
• Execution: Socat Reverse Shell Detected
• Execution: Suspicious OpenSSL Shared Object Loaded
• Exfiltration: Launch Remote File Copy Tools in Container
• Impact: Detect Malicious Cmdlines
• Impact: Remove Bulk Data from Disk
• Impact: Suspicious crypto mining activity using the Stratum Protocol
• Malicious Script Executed
• Malicious URL Observed
• Privilege Escalation: Attempt to Abuse Sudo For Privilege Escalation (CVE-2019-14287)
• Privilege Escalation: Polkit Local Privilege Escalation Vulnerability (CVE-2021-4034)
• Privilege Escalation: Sudo Potential Privilege Escalation (CVE-2021-3156)
• Reverse Shell
• Unexpected Child Shell

Control plane finding types

The following control plane detections are available with Event Threat Detection :

• Credential Access: AI Agent Anomalous Access to Metadata Service
• Defense Evasion: Folder Level TokenCreator Role Granted to AI Agent
• Defense Evasion: Organization Level TokenCreator Role Granted to AI Agent
• Defense Evasion: Project Level TokenCreator Role Granted to AI Agent
• Discovery: AI Agent Service Account Self-Investigation
• Discovery: AI Agent Unauthorized Service Account API Call
• Discovery: Evidence of Port Scanning from AI Agent
• Exfiltration: AI Agent Initiated BigQuery Data Exfiltration to External Table
• Exfiltration: AI Agent Initiated BigQuery Data Extraction
• Exfiltration: AI Agent Initiated BigQuery VPC Perimeter Violation
• Exfiltration: AI Agent Initiated CloudSQL Exfiltration to External Bucket
• Exfiltration: AI Agent Initiated CloudSQL Exfiltration to Public Bucket
• Initial Access: AI Agent Identity Excessive Permission Denied Actions
• Persistence: Sensitive AI Permission Added to Custom Role
• Persistence: Sensitive Role Granted by AI Agent
• Persistence: Sensitive Role Granted to External AI Agent
• Privilege Escalation: AI Agent Suspicious Cross-Project Access Token Generation
• Privilege Escalation: AI Agent Suspicious Cross-Project OpenID Token Generation
• Privilege Escalation: AI Agent Suspicious Token Generation Using Implicit Delegation
• Privilege Escalation: AI Agent Suspicious Token Generation Using signJwt

What's next

• Learn about Event Threat Detection .
• Learn about Agent Platform Threat Detection .
• Learn how to respond to AI threat findings .
• Refer to the Threat findings index .