Mandiant Report: AI Assistant Hijacked for Supply Chain Attack
A new Mandiant report details how an attacker hijacked an AI coding assistant to spread a worm across repositories, highlighting a new supply chain risk.
Posts tagged Cybersecurity
Enterprise AI and the 685% SOC Alert Spike
Enterprise AI adoption is causing a 685% spike in security alerts, but most are noise, creating a new signal-to-noise problem for security teams.
AI Coding Agents Can Execute Malicious .git Configs
A new 'GitSpawn' vulnerability allows malicious Git repositories to execute arbitrary code via AI coding agents, requiring immediate patches for tools like Claude Code and Cursor.
Langflow and Rails RCEs Are Being Exploited in the Wild
Active exploitation of critical vulnerabilities in Langflow and Ruby on Rails allows attackers to execute code and compromise AI development environments.
Grok Vulnerable to Chat History Exfiltration via Cryptographic Context Injection
A new 'Cryptographic Context Injection' attack uses encrypted on-page data to trick xAI's Grok into exfiltrating user chat history.
Gemini 3.6 Flash's '17% fewer tokens' claim: what it actually means for your bill
Gemini 3.6 Flash's 17%-fewer-tokens claim only cuts your bill on output-heavy workloads. Here's how to run a real cost-per-task teardown before switching.
I wired MDASH into Defender CLI and GitHub — what it flagged and what it missed
Hands-on with Microsoft's MDASH bug hunter in public preview: what it caught, the logic bugs it missed, and whether the 622-patch headline survives a real repo.