Search: “ai agents”

22 stories

Searchkeyword smart Sortlatest hot importance relevance

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

CategoryAll Vulnerability 712 AI safety & security 447 Exploit / PoC 439 Policy & legal 336 Ransomware 304 Malware 302 Industry 293 Threat actor 219 Data breach 199 Phishing & fraud 190 AI industry 131 AI tools & infra 94 Tools 82 Model release 81

SeverityAll critical 1515 high 538 medium 802 low 448 info 737

Can AI agents catch what your SOC misses?

Help Net SecuritySep 8, 09:20 UTC · Sep 8, 2025Exploit / PoC

45

New Agent Data Injection Attack Can Make AI Agents Misclick or Run Attacker Commands

The Hacker NewsJul 15, 00:00 UTC · Jul 15, 2026Exploit / PoC CVE-2025-327111

50

Top AI Agents Built to Catch Malicious Code Can Be Tricked Into Running It

The Hacker NewsJul 9, 05:17 UTC · Jul 9, 2026Exploit / PoC CVE-2026-39861

50

Strix: Open-source AI agents for penetration testing

Help Net SecurityNov 17, 00:00 UTC · Nov 17, 2025Exploit / PoC

45

Public GitHub Issue Could Trick GitHub Agentic Workflows Into Leaking Private Repo Data

The Hacker NewsJul 7, 14:07 UTC · Jul 7, 2026Exploit / PoC1

45

Tool Talk

Cisco TalosDec 19, 16:51 UTC · Dec 19, 2025Exploit / PoC

45

AI is the Top Cyber Priority for Defenders as Criminals Exploit it

Infosecurity MagazineMar 26, 13:15 UTC · Mar 26, 2026Exploit / PoC

45

Weaponizing machine learning to improve cyber defenses

Help Net SecurityMay 28, 09:46 UTC · May 28, 2020Exploit / PoC

45

An AI tool found 84 flaws in 5G network software and 23 of them still have no fix

Help Net SecurityAug 11, 00:00 UTC · Aug 11, 2026Exploit / PoC CVE-2026-8233

50

Google Vertex AI SDK Flaw Let Attackers Hijack Model Uploads via Bucket Squatting

The Hacker NewsJun 15, 00:00 UTC · Jun 15, 2026Exploit / PoC CVE-2026-24731

50

Your Purple Team Isn't Purple — It's Just Red and Blue in the Same Room

The Hacker NewsMay 11, 11:51 UTC · May 11, 2026Exploit / PoC

45

BlacksmithAI: Open-source AI-powered penetration testing framework

Help Net SecurityMar 2, 00:00 UTC · Mar 2, 2026Exploit / PoC1

45

Webmail CSS Attacks Expose a New Risk for AI

Security AffairsAug 9, 08:01 UTC · Aug 9, 2026Exploit / PoC

45

Unit 42 Threat Bulletin

Palo Alto Unit 42Mar 16, 11:21 UTC · Mar 16, 2026Exploit / PoC

45

Zen-AI-Pentest: Open-source AI-powered penetration testing framework

Help Net SecurityFeb 11, 00:00 UTC · Feb 11, 2026Exploit / PoC

45

n8n Token Exchange Flaw Could Let Attackers Log In as Users From Another Issuer

The Hacker NewsJul 15, 00:00 UTC · Jul 15, 2026Exploit / PoC CVE-2026-59208 CVE-2026-54305

50

Open-source AI pentesting tools are getting uncomfortably good

Help Net SecurityFeb 2, 00:00 UTC · Feb 2, 2026Exploit / PoC1

45

Researchers Trick AI Browsers Into Leaking Credentials

Infosecurity MagazineJun 24, 16:05 UTC · Jun 24, 2026Exploit / PoC

45

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

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

45

A SpaceX Security Engineer Used AI to Find a 19-Year

Security AffairsJun 1, 09:55 UTC · Jun 1, 2026Exploit / PoC

45

Cursor Flaw Lets Malicious Cloned Repositories Trigger Windows Code Execution

The Hacker NewsJul 15, 00:00 UTC · Jul 15, 2026Exploit / PoC CVE-2026-26268 CVE-2026-105911

50

Microsoft Says New Cybersecurity AI Model Helps MDASH Score 95.95% at Half the Cost

The Hacker NewsJul 28, 09:21 UTC · Jul 28, 2026Exploit / PoC

45