Security Command Center te ayuda a detectar e investigar amenazas a tus cargas de trabajo de IA y agentes de IA. Puedes revisar los hallazgos de los detectores que supervisan las amenazas generales relacionadas con la IA y de los detectores diseñados para los agentes de IA que se implementan en el entorno de ejecución de Agent Runtime.
Amenazas generales de IA
Las siguientes detecciones basadas en registros están disponibles en 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
Amenazas a los agentes implementados en Agent Runtime
Security Command Center realiza una supervisión del entorno de ejecución y del plano de control de los agentes de IA implementados en Agent Runtime.
Tipos de hallazgos del entorno de ejecución
Las siguientes detecciones de entorno de ejecución están disponibles con 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: Added Malicious Skill Executed -
Execution: Added Malicious Skill 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: Modified Malicious Skill Executed -
Execution: Modified Malicious Skill 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
Tipos de hallazgos del plano de control
Las siguientes detecciones del plano de control están disponibles en 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 Cross-Project Access Token Generation -
Privilege Escalation: AI Agent Cross-Project OpenID Token Generation -
Privilege Escalation: AI Agent Token Generation Using Implicit Delegation -
Privilege Escalation: AI Agent Token Generation Using signJwt
¿Qué sigue?
- Obtén información sobre Event Threat Detection.
- Obtén más información sobre Agent Platform Threat Detection.
- Aprende a responder a los hallazgos de amenazas de IA.
- Consulta el Índice de hallazgos de amenazas.