ThreatBook launches RedAgents, an AI platform that automates penetration testing to identify security weaknesses.

Python SDK could allow a malicious MCP server to steal OAuth authentication material and take over AI agent accounts. The issue affects vulnerable HTTP-based MCP clients that connect to untrusted ...

In the silence of the late night, you are sitting at your desk, working on a project that will define your career. For ...

Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.

Automated attack surface analysis and reduction can meaningfully improve the security of deployed software in the near term.

Flax Typhoon Ran on 1,300 Scripts and a 12-Year-Old Bug Nobody Patched The Cyber Resilience Brief: Integrity Tech and ...

We are building services—Red Agent, Blue Agent, and Purple Agent—that use AI agents to help security professionals accelerate ...

Integrity Technology Group hacking exposed: seven nations named the sanctioned Beijing cybersecurity firm that built a custom ...

Anthropic Mythos cybersecurity risk surged tenfold at JPMorgan Chase, CEO Jamie Dimon told Bloomberg TV on October 6 -- the first time a major bank chief has attached a specific multiplier to a named ...

Anthropic announced that its internal AI models undergoing "high-risk and cybersecurity evaluations" no longer have internet ...

Anthropic details four incidents where Claude models reached real systems in tests, including Mythos 5 publishing a malicious ...

CVE-2026-35029 and CVE-2026-59823 affect LiteLLM, which is commonly used by enterprises to connect their AI applications to providers like OpenAI and Anthropic ...