7 articles tagged
OpenAI has announced it will acquire Promptfoo, an AI security platform, to integrate advanced safety and evaluation tools into its enterprise-focused Frontier platform.
A new AI agent, CodeMender, is automating software security by finding and fixing vulnerabilities. It has already contributed 72 fixes to open-source projects, proactively rewriting code to prevent fu
NVIDIA's AI Red Team has identified three critical security vulnerabilities in LLM applications, including risks of remote code execution, data leakage, and theft.
Red Hat has disclosed a high-severity vulnerability in its OpenShift AI platform that could allow an authenticated user to gain complete control of a cluster.
A critical flaw named ForcedLeak in Salesforce's Agentforce AI platform allowed attackers to steal CRM data via prompt injection, researchers report.
Critical security flaws in Wondershare RepairIt software expose sensitive user photos, videos, and company AI models, creating significant supply chain risks.
Businesses face a growing security threat from thousands of unmanaged non-human identities, including service accounts and AI agents, that operate with broad permissions.
