New “Agentjacking” Attacks Could Hijack AI Coding Agents
Tenet Security researchers reveal how new “agentjacking” attacks could trick coding agents into executing arbitrary code
general
20 articles
Fake Software Tutorials on TikTok Spread Vidar Stealer
Threat actors push fake free-software tutorials on TikTok and Instagram to spread Vidar stealer
New SilabRAT Trojan Hijacks Sessions to Steal Crypto
MaaS trojan SilabRAT uses HVNC and browser cloning to hijack sessions and steal crypto
Cybersecurity Software Fails to Detect Fifth of Brower-Based Phishing Attacks
Menlo Security research warns that as enterprise applications become increasingly browser based, traditional cybersecurity tools leave them vulnerable to cyb...
Who Runs the Ransomware Group ‘The Gentlemen?’
A cybercrime group known as The Gentlemen has emerged as the second most active ransomware gang by victim count, rapidly attracting a talented pool of hacker...
New Fable 5 Is a "Mythos-Class" LLM Available to All, Anthropic Announces
Anthropic unveils Claude Mythos 5 and Fable 5, a restricted-access frontier AI model and guardrailed version for everyone to use
Over a Quarter of Identity Crime Victims Hit by Multiple Incidents, ITRC Data Shows
Nearly 26% of identity crime victims faced multiple incidents in the past year, as ITRC warns of a growing "multi-layered crisis"
Microsoft Fixes 200 CVEs in June Patch Tuesday
Microsoft has patched 200 vulnerabilities including three zero-days
A Record-Breaking Patch Tuesday for June 2026
Microsoft today released software updates to plug nearly 200 security holes across its Windows operating systems and supported software, a record number of f...
75% of Firms Deploy Vulnerable Code Amid Pressure on CISOs, Report Finds
Checkmarx report warns that business pressure is among the reason security leaders let security compliance slip
AI Coding Adoption Hits 97% but Governance Lags Behind
Most dev teams use AI coding assistants but only 30% have full governance in place
Critical phpBB Flaw Lets Attackers Hijack Any Account with One Request
Critical phpBB authentication bypass lets attackers hijack any account with one request
Google Releases Patch for Chrome Vulnerability Exploited in the Wild
The flaw, CVE-2026-11645, can allow a remote attacker to execute arbitrary code inside a sandbox via a crafted HTML page
Check Point Warns Critical Auth Bypass Bug Exploited in the Wild
Check Point says a critical vulnerability in its Remote Access VPN and Mobile Access solutions has been exploited by Qilin
Infosecurity Europe: Why JLR’s CISO Enforced In-Person Password Resets Following Cyber-Attack
Speaking at Infosecurity Europe, Ashish Shrestha, former CISO at Jaguar Land Rover revealed why he wanted over 30,000 employees to change their passwords in ...
WhatsApp Discovers NSO Group-Linked Spearphishing Attempts
Meta’s WhatsApp demands contempt ruling after users report NSO Group-linked phishing
North Korean Hackers Use Fake Coding Tasks to Steal Crypto
North Korean actor UNK_DeadDrop targeted developers with fake coding tasks to steal crypto
OpenAI Unveils ChatGPT Account Security Controls
OpenAI brings Lockdown Mode and Active Sessions to ChatGPT to curb prompt injection data theft
Infosecurity Europe: Prompt Injection Remains Unsolved, OWASP Researcher Warns
At Infosecurity Europe 2026, OWASP’s Ariel Fogel warned that prompt injection remains an “unresolved problem” within generative AI architecture