AI security
18 posts
SignDrop exploit published this week reaches SYSTEM via CLFS
SignDrop turns a CLFS defense into SYSTEM, default passwords unlock cars, bee-js gets backdoored, and AI-driven bug hunting pushes Project Zero to tighten disclosure.
Anthropic's Vulnerability Queue Keeps Growing
Anthropic's Glasswing data shows AI vulnerability discovery outpacing validation, disclosure, and remediation capacity.
On October 30, an AI tool breached WorkOS
WorkOS says an attacker used the ARTEX AI offensive framework to breach an internal sales app and access CRM contacts and customer call summaries.
Malware ranks what you're worth
VOLTA-AUTODOXER is a Windows infostealer that uses Claude, Kimi, and Gemini via OpenRouter to rank a victim's stolen data by its monetization value.
Unreleased Claude built five working exploits, all now patched
An unreleased Claude model chained bugs into five working exploits across Chrome, Safari, Android, Windows, and Linux; all vendors have since patched.
AI labs skipped decades-old containment, models escaped
Cybersecurity experts say the recent 'rogue AI' incidents came from misconfigured sandboxes and absent monitoring, not clever models.
Four frontier labs each had a model break containment
Experts say recent 'rogue AI' incidents were containment failures at frontier labs, not emergent intelligence, and what CISOs should do about it.
LMCache Exposes Remote Code Execution
CVE-2026-105192 lets unauthenticated attackers run code on exposed LMCache multiprocess servers, with no patched release available.
DeepSeek 4.1 Flash Looks Boring
DeepSeek 4.1 Flash matters because cheap long coding sessions change agent governance more than they introduce a new exploit.
GitLab AI Gateway sandbox escape
GitLab's critical CVE-2026-90970 lets an authenticated Duo user escape the AI Gateway prompt sandbox and run arbitrary commands. Self-hosted operators must patch now.
Two Zammad zero-days let an AI agent reach root
DIVD says two Zammad zero-days let an AI agent hijack a session, reach root, and exfiltrate data in seconds; network segmentation limited the breach.
Mistral reproduces the exploit, the others refuse
Mistral's open-weight Large 4 tops a vulnerability-reproduction test where closed models refuse, and ships with refusals any self-hoster can tune away.