Other
Artificial Foolishness: The Hidden Dangers of External-Facing LLMs
The rise of AI opens more doors to attackers
The rise of AI opens more doors to attackers
Indirect prompt injection (IPI) is an evolving threat vector targeting users of complex AI applications with multiple data sources, such as Workspace with Gemini. This t…
Posted by Adam Gavish, Google GenAI Security TeamIndirect prompt injection (IPI) is an evolving threat vector targeting users of complex AI applications with multiple data sources, such as Workspace with Gemini. This technique enables the attacker to influence the behavior of an LLM by injecting malicious instructions into the data or tools used by the LLM as it completes the user’s query. This may even be possible without any input directly from the user.IPI is not the kind of technical proble…
Cyber Briefs are monthly executive reports that aim to present an overview of the most relevant developments in cyber security, based exclusively on open sources, with a view to inform political leadership and senior management in its constituency. Additional information on any item in this Brief can be provided upon request. Cyber Briefs are TLP:CLEAR.
OpenClaw AI agents pose identity and data risks if deployed with broad cloud permissions. Learn how to find and secure these apps before an attacker does.
Group-IB researchers uncover an ongoing phishing campaign targeting major banks in the Philippines. This blog details how threat actors abuse trusted and legitimate platforms to deceive users and evade detection. It highlights a significant threat escalation with the successful hijacking of a legitimate domain to host malicious infrastructure, enabling threat actors to operate with even greater credibility and reduced detection.
See why the viral "three-finger test" is almost outdated, and how to build resilient security processes that protect your organization from identity-based attacks and social engineering, no matter how advanced the AI gets.
Fraudsters often target the accounts of the deceased or their grieving relatives. Here’s how to keep the scammers at bay.
An NPM supply chain attack struck the ubiquitous open-source axios library and Huntress has observed over a hundred affected devices.
2025 marked a special year in the history of vulnerability rewards and bug bounty programs at Google: our 15th anniversary 🎉🎉🎉! Originally started in 2010, our vulnerabi…
Posted by Dirk Göhmann, Tony Mendez, and the Vulnerability Rewards Program Team2025 marked a special year in the history of vulnerability rewards and bug bounty programs at Google: our 15th anniversary 🎉🎉🎉! Originally started in 2010, our vulnerability reward program (VRP) has seen constant additions and expansions over the past decade and a half, clearly indicating the value the programs under this umbrella contribute to the safety and security of Google and its users, but also highlighting…
The past four weeks have seen a slew of new cybersecurity wake-up calls that showed why every organization needs a well-thought-out cyber-resilience plan
Group-IB shows how Business Email Protection blocked Phantom Stealer phishing emails across different campaign waves.
Le 15 octobre 2025, F5 a publié un avis de sécurité concernant entre autres la vulnérabilité CVE-2025-53521. Celle-ci affecte BIG-IP APM et permet à un attaquant non authentifié d'exécuter du code à distance. Le 29 mars 2026, l'éditeur indique que cette vulnérabilité est exploitée activement. Le...
Le 15 octobre 2025, F5 a publié un avis de sécurité concernant entre autres la vulnérabilité CVE-2025-53521. Celle-ci affecte BIG-IP APM et permet à un attaquant non authentifié d'exécuter du code à distance. Le 29 mars 2026, l'éditeur indique que cette vulnérabilité est exploitée activement. Le...
A Claude Code Agent Dashboard
Global regulators are mandating fraud intelligence sharing. Learn how financial institutions can collaborate in real-time while maintaining privacy compliance through Distributed Tokenization.
Is your cybersecurity truly built to withstand today’s nuanced threats or is it just living on paper? Find out more.
We are opening our advanced Client-Side Security tools to all users, featuring a new cascading AI detection system. By combining graph neural networks and LLMs, we've reduced false positives by up to 200x while catching sophisticated zero-day exploits.
This year, AI agents took the center stage – as a defensive capability, but more pressingly as a risk many organizations haven't caught up with
Silver Fox is back in Japan, spoofing tax and HR emails timed to the one season when no one thinks twice about opening them
Modern digital security is at a turning point. We are on the threshold of using quantum computers to solve "impossible" problems in drug discovery, materials science, an…
That "friendly" prompt is a ClickFix scam. Learn about this advanced social engineering tactic that tricks users into running malicious code on their own systems, and why security resilience is your winning bet.
Posted by Eric Lynch, Product Manager, Android and Dom Elliott, Group Product Manager, Google Play Modern digital security is at a turning point. We are on the threshold of using quantum computers to solve "impossible" problems in drug discovery, materials science, and energy—tasks that even the most powerful classical supercomputers cannot handle. However, the same unique ability to consider different options simultaneously also allows these machines to bypass our current digital locks. This p…
Cómo GTFire abusa de Google Firebase y Google Translate para escalar campañas globales de phishing
Cloud VMs offer unmatched speed, scale and flexibility – all of which could eventually count for little if they’re left to fend for themselves
On 17 March 2026, Microsoft updated one of its January 2026 security advisories related to a remote code execution vulnerability in Microsoft SharePoint. Specifically, Microsoft raised the CVSS score and changed the FAQ section to indicate that the vulnerability could be exploited by an unauthenticated attacker. This vulnerability was added in the CISA's Known Exploited Vulnerabilities (KEV) catalogue on 18 March 2026. Additionally, three further RCE flaws affecting Microsoft SharePoint were ad…
Tracing the evolution of cloud phone technology from harmless social media engagement automation to industrial-scale financial fraud that’s invisible to modern detection systems.
Huntress now delivers ITDR for Google Workspace to protect identities against BEC, inbox rule manipulation, and account takeover, all with a 24/7 SOC-led response.