cognitive cybersecurity intelligence
Eduard Kovacs reports: Prompt injection and an expired domain could have been used to target Salesforce’s Agentforce platform for data theft. The attack method, dubbed ForcedLeak, was discovered by researchers at Noma Security, a company that recently raised $100 million for its AI agent security platform. Salesforce Agentforce enables businesses to build and deploy autonomous AI agents…
Source
Subscribe to HEAL Security Dispatch for the latest healthcare cybersecurity news and analysis.
A sophisticated phishing campaign has emerged targeting maintainers of packages on the Python Package Index (PyPI), employing domain confusion tactics to steal authentication credentials from
Fake trading platform ads on YouTube, Google spread malware scam SecurityBrief Australia
Emerging XCSSET Variant Threatens macOS App Developers Cyber Press
Proofpoint has announced four major innovations designed to secure the agentic workspace, where people and AI agents collaborate side by side. Proofpoint’s new collaboration and data
