I was mapping the command-and-control infrastructure behind a state-linked intrusion set when the query came back and effectively ended the exercise I…
News
Your orchestration framework choice is a security decision, not just an engineering one
Comparisons of LangChain, CrewAI and AutoGen are easy to find — dozens of guides this year cover the same ground: developer experience,…
Why you need a reliable AI agent kill switch
Recent high-profile rogue agent incidents involving OpenAI and Anthropic underscore the fact that organizations can’t put blind trust in their AI guardrails….
AI threat report: Rogue agents, workflow attacks
Malicious AI use and threats to AI systems are requiring cyber teams to double down on security fundamentals and rethink the future…
Ruby on Rails critical bug puts every image upload under scrutiny
A new critical vulnerability in the Ruby on Rails (“Rails”) web application framework, CVE-2026-66066, could turn a seemingly innocuous image into a…
ChainDrop credential stealing worm infects over 400 npm packages
A self-propagating worm-like attack is hitting the npm registry, having infected 444 packages from more than a dozen publishers so far. The…
Airlock Digital Unveils Agentic AI Control & Governance to Extend Preventative Endpoint Security
Airlock Digital, a leader in preventative endpoint security, today announced Agentic AI Control & Governance at Black Hat USA 2026. The new…
Critical Azure Cosmos DB flaw threatened cross-tenant database takeover
A critical vulnerability in Microsoft Azure’s Cosmos DB database service could have enabled attackers to escape the platform’s Gremlin query sandbox, execute…
The top cybersecurity product announcements from Black Hat 2026
Black Hat 2026 is shaping up to be another AI-heavy conference, but this year’s announcements suggest the industry is moving beyond simply…
Google ADK flaws reveal what happens when AI agents trust the wrong message
Security flaws in automated workflows in the GitHub repository for Google’s Agent Development Kit for Python could allow public-facing AI agents to…