⌁AI·CYBER·BRIEF▌

#CISA KEV

Vulnerabilities6 min read

LiteLLM sandbox escape now exploited in LLMjacking attacks: CISA adds CVE-2026-40217 to KEV

Attackers abused a LiteLLM guardrail sandbox escape to take over AI gateways and their keys, Google says. CISA set a Dec. 2 deadline. Upgrade and block the endpoint.

CVE-2026-40217LiteLLMCISA KEV
Vulnerabilities7 min read

GPUStack login bypass is being exploited to take over AI GPU clusters — CISA sets Nov. 12 deadline

A flaw in open-source GPUStack lets anyone become admin and run code on GPU workers. It is exploited in the wild and now in CISA's KEV catalog. Upgrade to 2.2.2+.

CVE-2026-102895CVE-2026-102894GPUStack
Vulnerabilities6 min read

Attackers are polling WordPress sites to catch the seconds-long update window in CVE-2026-119977

A race in WordPress core updates (4.7–7.1.3) briefly exposes an unauthenticated installer. CISA lists it as exploited. Block wp-content/upgrade before you update to 7.1.4.

CVE-2026-119977WordPressRace Condition
Vulnerabilities9 min read

AI-found PHP2Shell flaws are under active attack, CISA says — and now chained to root firewalls

CISA lists both PHP2Shell bugs as exploited, and Unit 42 says they were chained with a Linux kernel flaw to root firewalls. Fixed in PHP 8.5.12, 8.4.27, 8.3.36 and 8.2.35.

PHP2ShellPHPCVE-2026-109618
AI Threats7 min read

PoeLLM botnet mines crypto on exposed AI servers — patch LiteLLM and take Ollama off the internet

Lumen's Black Lotus Labs says a botnet active since April has hit thousands of internet-facing servers, mostly LiteLLM and Ollama, and hides its control server in a poem on GitHub.

LiteLLMOllamaBotnet
AI Threats7 min read

An AI agent breached a Dutch security non-profit via two Zammad zero-days — one is still unpatched

An AI agent chained two Zammad zero-days to break into DIVD's helpdesk. Both are now on CISA's exploited list, and the root flaw is still unpatched.

Agentic AIAutonomous AttacksZammad