Skip to content
Threat Feed
Subscribe

Vendor

CNCF

3 briefs RSS
high advisory

Autonomous AI Agents Pose New Supply Chain and Data Exfiltration Risks

This content introduces AI Detection and Response (AIDR) as a new cybersecurity category to address emerging threats from autonomous AI agents, including supply chain attacks and unintended data sharing, highlighting their ability to execute with inherited privileges across endpoints, SaaS, and cloud environments.

ClawHub +42 ai agentic-ai aidr supply-chain-attack data-exfiltration cloud-security endpoint-security saas-security
4t 16i updated
high advisory

CrowdStrike Uncovers New Prompt Injection Techniques

CrowdStrike's AI security research team has identified 18 new prompt injection techniques, expanding its taxonomy to over 200 methods, which enable adversaries to manipulate AI systems and agents through indirect means like hidden context, delayed triggers, and special token injection, leading to unauthorized actions such as data exfiltration or arbitrary command execution.

Gemini +36 prompt-injection ai llm ai-security cloud novel-technique
1r 4t 38i updated
high advisory

Exploitable Misconfigurations in AI Applications on Kubernetes

AI applications deployed on Kubernetes with exposed UIs and weak authentication can lead to remote code execution, credential theft, and access to sensitive data, as observed in MCP servers, Mage AI, and kagent deployments.

Microsoft Defender for Cloud +2 kubernetes ai misconfiguration cloud-security
2r 4t