Critical Vulnerability Exposes GitHub Agentic Workflows to Prompt Injection
Researchers show how attackers can use a crafted public GitHub Issue to trick AI-powered workflows into exposing data fr
共收录 1122 条相关情报。
← 返回所有主题Researchers show how attackers can use a crafted public GitHub Issue to trick AI-powered workflows into exposing data fr
The alleged victim, believed to be a small Ohio county, reportedly paid the extortion group to prevent the public releas
CVE-2026-20896
Attackers are exploiting the critical Gitea vulnerability CVE-2026-20896 to bypass authentication with a single HTTP hea
The audits are reportedly being spearheaded by CISA’s Attack Surface Evaluation team, a specialized unit tasked with con
CVE-2026-48282
Hackers are exploiting a recently patched critical vulnerability (CVE-2026-48282) in Adobe ColdFusion that carries a CVS
Researchers say the Iran-linked threat actor used an adaptable modular malware framework and compromised IT service prov
Tarah Wheeler is CISO at TPO Group, a firm that provides cybersecurity consultancy for high-stakes organizations. But de
The 16-year-old Januscape flaw affects Linux's KVM hypervisor, allowing attackers to escape virtual machines and potenti
The investment will accelerate Keyfactor's machine identity, PKI, and cryptographic security platform as enterprises pre
Securonix says the sophisticated framework abuses compromised websites, Blogspot, PowerShell, and fileless techniques to
Moving from isolated, technical data to a continuous risk lifecycle can help organizations align security controls with
The threat actor uses modular RATs and information stealers in financially motivated and cyber espionage campaigns. The
The PolinRider campaign has compromised more than 100 legitimate open source packages and repositories to deliver a back
Organizations are urged to patch after proof-of-concept code makes the Linux root escalation flaw easier to exploit. The
Researchers uncovered two campaigns embedding indirect prompt injections in malicious websites to exploit autonomous AI
Noteworthy stories that might have slipped under the radar: Anonymous-linked Canadian hacker jailed, researcher drops ze
Attack demonstrates how LLM agents can combine known exploitation techniques with real-time reasoning to automate comple
In April, ShinyHunters accessed the company’s corporate IT systems and stole patients’ personal and medical information.
Prosecutors say 19-year-old Peter Stokes was a member of Scattered Spider, the hacking group linked to more than 100 net
NetNut rented access to millions of compromised devices, allowing cybercriminals and nation-state actors to mask their i