Four vulnerabilities in CrewAI could be chained together via prompt injection for sandbox escape, remote code execution, and ...

A team of researchers from UC Berkeley have demonstrated that eight AI agent benchmarks can be manipulated to produce ...

OpenAI revoked its macOS signing certificate after a malicious Axios dependency incident on March 31, 2026, preventing ...

The open-source project maps directly to OWASP’s top 10 agentic AI threats, aiming to curb issues like prompt injection, ...

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.

Although executed by different attackers – Axios by North Korean-linked goons, and Trivy et al. by a loosely knit band of ...

Attackers weaponized critical RCE within hours, prompting CISA to add the flaw to its KEV catalog and set an urgent patch deadline.

A cyber attack hit LiteLLM, an open-source library used in many AI systems, carrying malicious code that stole credentials such as environment variables, SSH keys, and passwords.

Infosecurity outlines key recommendations for CISOs and security teams to implement safeguards for AI-assisted coding ...

Cloudflare says dynamically loaded Workers are priced at $0.002 per unique Worker loaded per day, in addition to standard CPU and invocation charges ...

Up to four npm packages on Axios were replaced with malicious versions, in one of the most sophisticated supply chain attacks ...