Google DeepMind paper warns AI agents can be hijacked by malicious web content
Google DeepMind researchers are warning that autonomous AI agents face a growing security problem from what they call “AI Agent Traps.” In their paper, the…
More than 2,000 internet-exposed FortiClient EMS servers raise concern as Fortinet confirms active exploitation
More than 2,000 FortiClient EMS instances appear reachable from the public internet at a time when Fortinet has confirmed in-the-wild exploitation of a critical FortiClient…
CISA adds actively exploited TrueConf flaw to KEV and gives agencies until April 16 to patch
CISA has added CVE-2026-3502, a TrueConf Client vulnerability, to its Known Exploited Vulnerabilities catalog after confirming active exploitation. The agency says federal civilian agencies must…
METATRON brings local AI-assisted pentesting to Linux with offline LLM analysis
A new open-source security tool called METATRON is drawing attention because it runs AI-assisted penetration testing workflows entirely on the local machine. According to the…
36 fake Strapi npm packages used in targeted attack on crypto payment infrastructure
A newly uncovered npm supply chain attack used 36 malicious packages disguised as Strapi plugins to target a cryptocurrency payment environment with Redis exploitation, credential…
ResokerRAT turns Telegram into a stealth control channel for Windows attacks
A newly documented Windows remote access trojan called ResokerRAT uses Telegram’s Bot API as its command-and-control channel, giving attackers a way to control infected systems…
Fake Microsoft Teams meeting pages are now being used to deliver malware
Security researchers are warning about a fresh phishing campaign that uses fake Microsoft Teams meeting pages to trick users into installing malware. The reported lure…
Critical Claude Code flaw could bypass deny rules with long command chains
Anthropic has shipped a fix for a Claude Code security issue that could let long shell command chains slip past developer-set deny rules in older…
Axios npm compromise pushed cross-platform malware through poisoned releases
Developers who installed [email protected] or [email protected] on March 31 should treat those systems as compromised. Axios maintainer Jason Saayman confirmed that two malicious versions were…
Malware was served through ilspy.org, not ILSpy’s official site, maintainers say
A malicious site posing as ILSpy appears to have redirected visitors toward malware on April 6, 2026, but one key part of the sample article…
November 21, 2025
1 comment 
