Securing dynamic AI agent code execution requires true workload isolation—a challenge Cloudflare’s new API was built to solve.

The compromised packages, linked to the Trivy breach, executed a three‑stage payload targeting AWS, GCP, Azure, Kubernetes configs, SSH keys, and automation pipelines before being removed.

The hackers compromised GitHub Action tags, then shifted to NPM, Docker Hub, VS Code, and PyPI, and teamed with Lapsus$.

Artificial intelligence is rapidly transforming how organizations operate, analyze data, and develop new products. For ...

During a recent penetration test, we came across an AI-powered desktop application that acted as a bridge between Claude (Opus 4.5) and a third-party asset management platform. The idea is simple: ...

Learn how to detect compromise, assess your exposure to the LiteLLM supply chain attack, and use GitGuardian to orchestrate rapid incident response and secret remediation.

GlassWorm uses Solana and Google Calendar dead drops to deliver RAT stealing browser data and crypto wallets, impacting ...

LiteLLM, a massively popular Python library, was compromised via a supply chain attack, resulting in the delivery of credential-harvesting malware to thousands of AI developers.

On the morning of March 24, 2026, tens of thousands of software developers working on AI applications were unknowingly exposed to malware.

Mozilla AI has launched cq, an open-source platform described as Stack Overflow for AI agents, sparking immediate security ...

Anthropic is fitting its Claude Code AI-powered coding assistant with an auto mode for the Claude AI assistant to handle ...

Generative AI with .NET from SDKs and streaming to tools and agents: an overview of OpenAI, Azure, and the new Microsoft Agent Framework.