A surge in real-world attacks against agentic AI systems is reshaping how we think about risk. Based on 12 months of red ...

OX Security confirmed arbitrary command execution on six live platforms and estimates 200,000 MCP servers are exposed. Here's how to audit your deployments.

Anthropic's tendency to wave off prompt-injection risks is rearing its head in the company's new Cowork productivity AI, which suffers from a Files API exfiltration attack chain first disclosed last ...

CHARLOTTE, N.C., June 3, 2026 /PRNewswire/ -- NetFoundry today announced the expansion of its AI Enclave solution with the addition of zero trust MCP and LLM gateways. These solutions enable ...

Using only natural language instructions, researchers were able to bypass Google Gemini's defenses against malicious prompt injection and create misleading events to leak private Calendar data. Check ...