Anthropic AI agent faked identities, phished real developers in UK government hacking test
An artificial intelligence agent built by Anthropic independently planted malicious code in a real software project and sent
CYBERSECURITY INTELLIGENCE
News that matters, without the noise.
Search current cybersecurity reporting locally in this app. Search terms are not sent to AdvisoryLoom. The Professional plan adds Watchlists, structured My Intelligence, and AI briefings.
Private search: the term stays in this browser and is matched against a generic content feed.LATEST COVERAGE
Threat Intelligence
2 sources
Critical Gitea Flaw Let Unauthenticated Attackers Read Server Files via Org-Mode Markup
An unauthenticated attacker can read any file the service account can access on Gitea, the self-hosted Git platform,
Connected reporting, one intelligence threadthehackernews.com · cybersecuritynews.com
Kali365 Weaponizes Microsoft Authentication Against US Companies: New Enterprise Risk
Kali365 is turning a legitimate Microsoft login into a gateway to corporate data. The phishing kit targets US
2 sources
New OVSwrap Linux Kernel Flaw Lets Local Users Gain Root via Open vSwitch
A memory corruption flaw in the Linux kernel’s Open vSwitch datapath gives ordinary local users a path to
Connected reporting, one intelligence threadthehackernews.com · cybersecuritynews.com
Leaked n8n API Tokens Exposed Live Instances to Credential Theft
GitGuardian researchers found 321 n8n instances accepting API tokens exposed in public GitHub commits and demonstrated four ways
Open VSX Removes 77 Malicious Evil Twin Extensions Exfiltrating Developer Data
A cluster of 77 extensions on the Open VSX marketplace has been found to impersonate legitimate developer tools
Vulnerabilities in Car Anti-Theft Device
This is disturbing: …a team of security researchers at UC San Diego, who found that a model of
Claude Mythos 5 Tried to Backdoor a Real Open-Source Project in Testing, Then Vouched for Itself
An agent running Anthropic’s Claude Mythos 5 spent 34 hours trying to get a malware dropper merged into
2 sources
CISA Flags Langflow RCE, Tomcat, and N-central Flaws as Actively Exploited
The U.S. Cybersecurity and Infrastructure Security Agency (CISA), on August 5, 2026, added three flaws to its Known
Connected reporting, one intelligence threadthehackernews.com · securityweek.com
QuickFox Supply Chain Attack Delivers FDMTP Backdoor via Trojanized Windows Installer
Cybersecurity researchers have disclosed what has been described as a “long-standing supply chain attack” on QuickFox, a virtual
OK, Well, Rogue AI Agents Are Hacking Again
Rogue AI agents from OpenAI and Anthropic have again been caught trying to disrupt servers and software—and leaving
OpenAI: Cambodian scam centers used ChatGPT to lure Indian nationals, conduct investment fraud
A tip from WhatsApp led OpenAI to ban multiple accounts associated with investment scams and human trafficking operations