Hackers Can Turn AI Workflows Into Privileged Data-Stealing Proxies Without Jailbreaking Models
Enterprise AI workflows can be vulnerable to misuse that exposes sensitive information without prompt injection, account compromise, or
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
Latest cybersecurity news
Critical Check Point VPN Vulnerabilities Enable Remote Code Execution Attacks
Check Point Software has disclosed and patched two critical VPN-related vulnerabilities, CVE-2026-85102 and CVE-2026-85103, both carrying a maximum
UK appoints new commander of National Cyber Force
The individual has not yet been avowed — the formal process in Britain by which an intelligence or
Check Point Discloses Two 9.8-Rated VPN Certificate Flaws Enabling Unauthenticated RCE
Check Point has patched two critical vulnerabilities in the way its firewall and management products handle VPN certificates.
PaperCut Attacker Uses Hundreds of AI Agents to Compromise 440+ Instances
A suspected Russian-speaking cyber actor has been attributed to the use of artificial intelligence (AI) to devise exploits
Gigabud Creates Android Work Profiles to Hide From Banking App Malware Checks
The Gigabud banking trojan now installs a second Android app that creates a work profile on an infected
RHSA-2026:66347: Important: freerdp security update
An update for freerdp is now available for Red Hat Enterprise Linux 9. Red Hat Product Security has
Palo Alto Networks security advisory (AV26-905)
<article data-history-node-id="8213" about="/en/alerts-advisories/palo-alto-networks-security-advisory-av26-905" class="cccs-threats full clearfix"> <div class="content"> <div class="layout layout–onecol"> <div class="layout__region layout__region–content"> <div data-block-plugin-id="extra_field_block:node:cccs_threats:links" class="block block-layout-builder
FBI Publishes First-Ever Cyber Strategy, With Focus on Disrupting Threat Actors
The new document appears to be part of a broader shift by the US government towards the proactive
LiteLLM Flaws Let Attackers Execute Code as Root and Steal Cloud Credentials
LiteLLM deployments can expose far more than an organization’s AI spending. Newly disclosed weaknesses in the open-source gateway