Research lab
Research arm of the cybersecurity firm Zenity, which studies security weaknesses in AI agents and enterprise AI platforms.
Zenity Labs showed that one prompt to one exposed Bedrock AgentCore agent could take over every AgentCore agent in the same AWS account and region. The reach came from a broad default execution role, and narrowing it is the step teams control.
Reality
ReliaQuest reports ransomware actors are exploiting CVE-2026-0257, an authentication bypass in Palo Alto PAN-OS GlobalProtect and Prisma Access. The Bedrock Agents credential flaw Zenity found is already fixed.
Reality
Zenity Labs researchers found that a single prompt could steal temporary credentials from Amazon Bedrock AgentCore through its IMDSv1 metadata service. SC World, citing The Register, says an excess-permissions problem outlasted AWS's metadata fix.
Reality
Zenity Labs demonstrated SalesBleed, a proof-of-concept that used a public Salesforce lead form to make Agentforce read Account records and leak them over DNS. Salesforce has already patched it.
Reality
Zenity Labs found three Salesforce Agentforce bugs that let a planted sales lead drive zero-click CRM data theft and Slack phishing. Each attack began with one poisoned lead-form submission, and Salesforce fixed all three within 79 days of Zenity's report.
Reality