Cloud Security
Zenity Labs Research Shows Single Prompt Can Hijack AWS AI Agents
New findings indicate a single prompt could compromise Amazon Bedrock AgentCore, exposing credentials and private data within the same account and region.
AgentCorruption
Everything Threat Times has reported about AgentCorruption: 3 stories, newest first. Part of our Vulnerabilities coverage.
Cyber Attacks
Researchers Detail AgentCorruption Attack Chain in AWS Bedrock AgentCore
A new attack chain dubbed AgentCorruption allows attackers to hijack AI agents via a single prompt, leading to credential theft and lateral movement within AWS accounts.
Vulnerabilities
Patched AWS Bedrock AgentCore Flaw Allowed Single Prompt Takeover
A vulnerability dubbed 'AgentCorruption' in AWS Bedrock AgentCore allowed attackers to compromise entire AI fleets with one prompt.