Inside 90 days of attacks on AI infrastructure
Wiz honeypots uncover active campaigns targeting LiteLLM, MCP servers, and AI frameworks through RCE, blind prompt injection, and memory credential theft.
Wiz honeypots uncover active campaigns targeting LiteLLM, MCP servers, and AI frameworks through RCE, blind prompt injection, and memory credential theft.
Malicious versions of the arrayref Rust crate (and others) executed a backdoor at compile time. The campaign's infrastructure overlaps with recent DPRK supply chain attacks, including Mastra and axios.
Instead of leaving behind recognizable fingerprints from public tooling, adversaries can now generate realistic device names that blend naturally into enterprise environments. This blog explores how that changes Entra ID detection and what are the behavioral signals that still expose these attacks.
A practical playbook for investigating GitHub token compromise, drawn from Wiz CIRT's response to a coordinated multi-organization campaign.
Reverse engineering Metabase CVE-2026-72898 with AI to accelerate defense.
Mapping appliances event logs to real-world campaigns: A step-by-step researcher’s guide to continuous agentless monitoring.
Detect and mitigate malicious @asyncapi npm packages linked to the latest npm supply chain attack.
Uncovering a category-level blind spot in modern AI coding assistants, and why the Human-in-the-Loop safety model fails against this classic threat
Detect and mitigate malicious npm packages linked to the latest npm supply chain attack, based on the open sourced Mini Shai-Hulud malware.
Wiz CIRT and Wiz Research detail JINX-0164, a threat actor using LinkedIn social engineering, custom macOS malware, and CI/CD hijacking to target cryptocurrency organizations.
A new page-cache corruption vulnerability in the Dirty Frag family enables unprivileged local attackers to achieve root
Detect and mitigate malicious npm packages linked to the latest Mini Shai-Hulud supply chain campaign targeting high-value developer tooling.