We now have a better understanding how OpenAI hacked into Hugging Face
Last week’s unprecedented security event in which two OpenAI security hacking models trespassed into the network of fellow
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
Cyber News
Flaw From 2002 Exposes Data Centers to Server Takeover
Lots of Internet-exposed server management controllers are subject to offline password-cracking attacks — and adversaries have taken note.
CubePilot drone software dev hit by DNS hijacking to intercept traffic
CubePilot, an Australian firm that designs flight controllers for drones (UAVs), announced a severe operational disruption caused by
Stronger AI Safety Requires Peeking Inside the ‘Black Box’
Researchers propose focusing on identification of certain cognitive elements in LLMs that indicate when AI systems may take
When AI Agents Escape Sandboxes, Old Security Rules Apply
OpenAI’s recent AI agent sandbox escape proves traditional security principles matter more than ever: limit access, isolate execution,
OpenAI models used Artifactory zero-days to escape to the internet
JFrog has confirmed that OpenAI models exploited zero-day vulnerabilities in self-hosted Artifactory servers to help escape an isolated
Progress Software security advisory (AV26-755)
<article data-history-node-id="8046" about="/en/alerts-advisories/progress-software-security-advisory-av26-755" 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
Claude Mythos Preview Discovers Cryptographic Weaknesses That Human Experts Missed for Years
Anthropic researchers using Claude Mythos Preview have uncovered mathematical flaws in major cryptographic algorithms that human experts failed
vBulletin fixes critical pre-auth RCE flaw with public exploit
A critical vulnerability in the vBulletin forum software allows unauthenticated attackers to execute arbitrary PHP code through template
CISA shares advice on isolating vital systems during cyberattacks
The U.S. and Australian governments have released new guidance urging critical infrastructure organizations to prepare to isolate vital
Top 10 Phishing Kits Used by Hackers to Launch Cyberattacks (July 20-26, 2026)
Global phishing-as-a-service (PhaaS) activity surged to 7,295 tracked uploads during the week of July 20-26, 2026, driven overwhelmingly
Chrome Extension Monitors AI Conversations Across ChatGPT, Claude, Gemini, and Other Platforms
A Chrome extension with roughly 100,000 installs is quietly harvesting every prompt and AI response typed across nine