Topic: ai-security

12 articles

Explore our coverage of ai-security — 12 curated articles, summaries, and related resources from the Inblix archive.

Zoom flaw let attackers hijack devices with zero clicks — patched after AI found it in a day

The Verge AI · Aug 11, 2026 · 2 min read

A vulnerability that would have once taken a nation-state team months to exploit was cracked in a single day using fewe...

AI News

Hidden white text in a PDF can drain your Jira secrets via Atlassian's Rovo

The Decoder · Aug 10, 2026 · 2 min read

A single PDF with white-on-white text is all an attacker needs to vacuum up sensitive corporate data from Jira and Conf...

Industry

Cloudflare open-sources the AI vibe-coding platform 2,000+ employees already use daily

Ars Technica AI · Aug 6, 2026 · 2 min read

Cloudflare just dropped its internal secret weapon onto GitHub. The company open-sourced Cloudflare OS, a platform that...

AI News

NVIDIA’s SkillSpector scans AI agent skills, finds 100% of malicious code

MarkTechPost · Aug 4, 2026 · 2 min read

NVIDIA has released a new open-source tool called SkillSpector, and a hands-on test shows it’s remarkably effective at...

AI News

Mend.io drops a 7-artifact guide to lock down AI agents before your AppSec team loses track

MarkTechPost · Aug 3, 2026 · 3 min read

Traditional application security is built on a simple premise: the code is the blueprint. An agentic AI system laughs a...

AI News

AI found 23,000 bugs; attackers used 1. That's the real vulnerability story

The Decoder · Aug 2, 2026 · 2 min read

Here's a number that should reset the conversation around AI and cybersecurity: 23,000. That's how many findings Anthro...

AI News

Researcher’s Copilot worm hides in Word docs and spreads unseen for 144 days

The Decoder · Aug 1, 2026 · 2 min read

Håkon Måløy didn't just find a vulnerability. He built a self-spreading worm that turns Microsoft Copilot against its u...

Industry

Anthropic’s Mythos model kills NIST quantum-resistant crypto contender HAWK

Ars Technica AI · Jul 29, 2026 · 2 min read

HAWK, a digital signature algorithm vying to become a standard defense against quantum computer attacks, is dead. Its c...

Product

AI's dark side: Malicious use will lower attack costs, new report warns

OpenAI Blog · Jul 20, 2026 · 3 min read

A new multi-institutional report is drawing a bullseye on a future where artificial intelligence doesn't just malfuncti...

Product

OpenAI, US CAISI find agent hijack bugs fixed in a day

OpenAI Blog · Jul 13, 2026 · 2 min read

The line between traditional cybersecurity and AI-specific exploits just got blurrier — and that's exactly the point of...

Research

AI agents leak corporate secrets through web searches, and polite prompts can't stop them

Hugging Face Blog · Jun 18, 2026 · 2 min read

Here's a scenario that should keep security teams up at night. A healthcare firm deploys a deep research agent. It has...

Research

Hugging Face now scans all 2.2M public models with VirusTotal for malware

Hugging Face Blog · Oct 22, 2025 · 2 min read

Starting today, every one of the more than 2.2 million public model and dataset repositories on the Hugging Face Hub is...