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

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

Over 1,000 exposed ComfyUI instances exploited via unauthenticated code execution, enabling Monero mining and botnet expansion.

After hacking Trivy, TeamPCP moved to compromise repositories across NPM, Docker Hub, VS Code, and PyPI, stealing over 300GB ...

The Cybersecurity and Infrastructure Security Agency (CISA) is warning that hackers are actively exploiting a critical ...

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

The compromised packages, linked to the Trivy breach, executed a three‑stage payload targeting AWS, GCP, Azure, Kubernetes ...

A cyber attack hit LiteLLM, an open-source library used in many AI systems, carrying malicious code that stole credentials ...

Strapi plugins exploit Redis and PostgreSQL via postinstall scripts, enabling persistent access and data theft.

Cloudflare’s Dynamic Workers aim to simplify how enterprises execute AI-generated code, signaling a shift toward lightweight, ...

A vulnerability in the telnetd of GNU Inetutils allows attackers from the network to inject malicious code – without prior authentication. An update to patch the security hole is not yet available.

Threats actors pounced on the vulnerability within hours of its disclosure, demonstrating that organizations have little time ...