Search: “guardrails”

90 stories

Searchkeyword smart Sortlatest hot importance relevance

DomainAll Cyber AIWindow24h 3d 7d 30d AllIn the wild Important only Show duplicates

CategoryAll Vulnerability 277 AI safety & security 266 Policy & legal 142 Exploit / PoC 90 Malware 82 Threat actor 73 Data breach 67 Ransomware 56 Phishing & fraud 28 AI policy 26 Industry 25 Model release 18 Tools 13 AI tools & infra 9

SeverityAll critical 391 high 158 medium 380 low 116 info 143

ThreatsDay Bulletin: Claude Chat Abuse, NastyC2 npm Packages, Device

The Hacker NewsJun 18, 15:29 UTC · Jun 18, 2026Exploit / PoC CVE-2026-20127

60

Anthropic disables new models after government calls them a national security concern

CyberScoopJun 13, 18:30 UTC · Jun 13, 2026Exploit / PoC in the wild

60

Autonomous AI-driven worm can reason its way through corporate networks

Help Net SecurityJun 3, 00:00 UTC · Jun 3, 2026Exploit / PoC in the wild

60

Why you need BAS and autonomous pentesting together

Help Net SecurityJun 2, 00:00 UTC · Jun 2, 2026Exploit / PoC

60

White House cyber official: identity security matters more than ever in the age of AI

CyberScoopMay 14, 20:15 UTC · May 14, 2026Exploit / PoC in the wild

60

Flaw in Claude’s Chrome extension allowed ‘any’ other plugin to hijack victims’ AI

CyberScoopMay 8, 13:14 UTC · May 8, 2026Exploit / PoC in the wild

60

Anthropic Project Glasswing to Use AI to Fix Software Bugs With AI

Infosecurity MagazineApr 8, 11:30 UTC · Apr 8, 2026Exploit / PoC

60

ChatGPT Security Issue Enabled Data Theft via Single Prompt

Infosecurity MagazineMar 31, 13:01 UTC · Mar 31, 2026Exploit / PoC in the wild

60

Cybersecurity jobs available right now: December 23, 2025

Help Net SecurityMar 27, 12:20 UTC · Mar 27, 2026Exploit / PoC

60

No, it’s not ‘unnecessarily burdensome’ to control your own data

CyberScoopMar 10, 20:11 UTC · Mar 10, 2026Exploit / PoC in the wild

60

From fake nudes to fake quotes: AI deepfakes plagued Olympic athletes

CyberScoopMar 2, 13:05 UTC · Mar 2, 2026Exploit / PoC in the wild

60

Anthropic accuses Chinese labs of trying to illicitly take Claude’s capabilities

CyberScoopFeb 23, 21:02 UTC · Feb 23, 2026Exploit / PoC in the wild

60

Asian State-Backed Group TGR-STA-1030 Breaches 70 Government, Infrastructure Entities

The Hacker NewsFeb 7, 11:03 UTC · Feb 7, 2026Exploit / PoC

60

Hundreds of Malicious Crypto Trading Add

Infosecurity MagazineFeb 3, 16:30 UTC · Feb 3, 2026Exploit / PoC

57

Week in review: Microsoft fixes exploited Office zero-day, Fortinet patches FortiCloud SSO flaw

Help Net SecurityFeb 1, 00:00 UTC · Feb 1, 2026Exploit / PoC in the wildCVE-2026-21509 CVE-2026-24858 CVE-2025-8088+1 CVEs

60

HackerOne rolls out industry framework to support ‘good faith’ AI research

CyberScoopJan 20, 20:59 UTC · Jan 20, 2026Exploit / PoC

60

Policymakers grapple with fallout from Chinese AI

CyberScoopDec 18, 23:08 UTC · Dec 18, 2025Exploit / PoC

60

New cybersecurity guidance paves the way for AI in critical infrastructure

CyberScoopDec 11, 12:00 UTC · Dec 11, 2025Exploit / PoC in the wild

60

Microsoft Issues Security Fixes for 56 Flaws, Including Active Exploit and Two Zero

The Hacker NewsDec 10, 15:09 UTC · Dec 10, 2025Exploit / PoC in the wildCVE-2025-62223 CVE-2025-62221 CVE-2025-54100+6 CVEs1

60

New research finds that Claude breaks bad if you teach it to cheat

CyberScoopNov 24, 22:41 UTC · Nov 24, 2025Exploit / PoC in the wild

60

When trust turns toxic: Lessons from the Salesloft Drift incident

CyberScoopNov 24, 11:00 UTC · Nov 24, 2025Exploit / PoC in the wild

60

Researchers question Anthropic claim that AI

Ars Technica · SecurityNov 15, 00:00 UTC · Nov 15, 2025Exploit / PoC

60

AI is forcing boards to rethink how they govern security

Help Net SecurityNov 12, 00:00 UTC · Nov 12, 2025Exploit / PoC in the wild

60

Two Critical Flaws Uncovered in Wondershare RepairIt Exposing User Data and AI Models

The Hacker NewsSep 24, 13:55 UTC · Sep 24, 2025Exploit / PoC CVE-2025-10643 CVE-2025-106441

60

ShadowLeak Zero-Click Flaw Leaks Gmail Data via OpenAI ChatGPT Deep Research Agent

The Hacker NewsSep 20, 05:32 UTC · Sep 20, 2025Exploit / PoC1

45

F5 to acquire AI security firm CalypsoAI for $180 million

CyberScoopSep 11, 17:55 UTC · Sep 11, 2025Exploit / PoC in the wild

60

How security teams are putting AI to work right now

Help Net SecurityAug 18, 00:00 UTC · Aug 18, 2025Exploit / PoC

45

Guess what else GPT

CyberScoopAug 13, 13:37 UTC · Aug 13, 2025Exploit / PoC in the wild

60

Wiz Uncovers Critical Access Bypass Flaw in AI

The Hacker NewsJul 30, 07:43 UTC · Jul 30, 2025Exploit / PoC in the wild

60

Critical Golden dMSA Attack in Windows Server 2025 Enables Cross

The Hacker NewsJul 21, 06:31 UTC · Jul 21, 2025Exploit / PoC

60

Why skipping security prompting on Grok’s newest model is a huge mistake

CyberScoopJul 14, 19:43 UTC · Jul 14, 2025Exploit / PoC in the wild

60

DHS Secretary Noem: CISA needs to get back to ‘core mission’

CyberScoopApr 30, 15:27 UTC · Apr 30, 2025Exploit / PoC in the wild

60

⚡ THN Weekly Recap: Top Cybersecurity Threats, Tools and Tips [3 February]

The Hacker NewsFeb 4, 11:56 UTC · Feb 4, 2025Exploit / PoC in the wildCVE-2025-24085 CVE-2024-41710 CVE-2025-0626+30 CVEs

60

Invisible text that AI chatbots understand and humans can’t? Yep, it’s a thing.

Ars Technica · SecurityOct 15, 00:00 UTC · Oct 15, 2024Exploit / PoC1

45

OpenAI says it has disrupted 20-plus foreign influence networks in past year

CyberScoopOct 9, 19:25 UTC · Oct 9, 2024Exploit / PoC in the wild

60

GenAI buzz fading among senior executives

Help Net SecurityAug 26, 00:00 UTC · Aug 26, 2024Exploit / PoC

60

Practical Guidance For Securing Your Software Supply Chain

The Hacker NewsJun 26, 09:52 UTC · Jun 26, 2024Exploit / PoC

60

State-backed hackers are experimenting with OpenAI models

CyberScoopFeb 14, 12:00 UTC · Feb 14, 2024Exploit / PoC in the wild

60

New PoC Exploit for Apache OfBiz Vulnerability Poses Risk to ERP Systems

The Hacker NewsJan 15, 00:00 UTC · Jan 15, 2024Exploit / PoC in the wildCVE-2023-51467 CVE-2023-49070 CVE-2020-9496+2 CVEs

60

California passes first-in-the

CyberScoopSep 16, 02:09 UTC · Sep 16, 2023Exploit / PoC in the wild

60