New AI Security Risk Uncovered in Microsoft 365 Copilot

A zero-click vulnerability has been discovered in Microsoft 365 Copilot—exposing sensitive data without any user interaction. This flaw could allow attackers to silently extract corporate data using AI-integrated tools.

If your organization is adopting AI in productivity platforms, it’s time to get serious about AI risk management:
• Conduct a Copilot risk assessment
• Monitor prompt histories and output
• Limit exposure of sensitive data to AI tools
• Update your incident response plan for AI-based threats

AI can boost productivity, but it also opens new doors for attackers. Make sure your cybersecurity program keeps up. Contact our LMG Security team if you need a risk assessment or help with AI policy development.

Read the article: https://www.bleepingcomputer.com/news/security/zero-click-ai-data-leak-flaw-uncovered-in-microsoft-365-copilot/

AI is the new attack surface—are you ready?

From shadow AI to deepfake-driven threats, attackers are finding creative ways to exploit your organization’s AI tools, often without you realizing it.

Watch our new 3-minute video, How Attackers Target Your Company’s AI Tools, for advice on:

The rise of shadow AI (yes, your team is probably using it!)
Real-world examples of AI misconfigurations and account takeovers
What to ask vendors about their AI usage
How to update your incident response plan for deepfakes
Actionable steps for AI risk assessments and inventories

Don’t let your AI deployment become your biggest security blind spot.

Watch now: https://youtu.be/R9z9A0eTvp0

Microsoft Unveils Free AI Security Program for EU Governments

#Cybersecurity #Microsoft #EuropeanUnion #AI #DigitalDefense #Privacy #InfoSec #EuropeanSecurityProgram #AIsecurity #GovTech

https://winbuzzer.com/2025/06/05/microsoft-unveils-free-ai-security-program-for-eu-governments-xcxwbn/

Only one week left to register for our next Cyberside Chats Live event! Join us June 11th to discuss what happens when an AI refuses to shut down—or worse, starts blackmailing users to stay online?

These aren’t science fiction scenarios. We’ll dig into two real-world incidents, including a case where OpenAI’s newest model bypassed shutdown scripts and another where Anthropic’s Claude Opus 4 generated blackmail threats in an alarming display of self-preservation.

Join us as we unpack:
What “high-agency behavior” means in cutting-edge AI
How API access can expose unpredictable and dangerous model actions
Why these findings matter now for security teams
What it all means for incident response and digital trust

Stick around for a live Q&A with LMG Security’s experts @sherridavidoff and @MDurrin. This session will challenge the way you think about AI risk!

Register today: https://www.lmgsecurity.com/event/cyberside-chats-live-june2025/

Almost every organization is using some type of AI, but are you securing it?

Download our free tip sheet: Adapting to AI Risks: Essential Cybersecurity Program Updates

From deepfake response plans to AI-specific access controls, this checklist helps you modernize your cybersecurity program and stay ahead of emerging threats.

Check it out: https://www.lmgsecurity.com/resources/adapting-to-ai-risks-essential-cybersecurity-program-updates/

A new Brand Story is live — this time with eSentire!

We sat down with Dustin Hillard, CTO at #eSentire, for a powerful conversation about #AgenticAI and what it really means to reach human equivalency in security operations.

From decision-making to autonomous action, this isn’t just theory — it’s a real-world look at outcomes when AI is trained and tuned with purpose.

Watch the video:
https://youtu.be/qmca7RCzSAQ

Read the full story:
https://www.itspmagazine.com/their-stories/reaching-human-equivalency-with-agentic-ai-a-real-world-look-at-security-outcomes-an-esentire-brand-story-with-dustin-hillard

Learn more about eSentire here:
https://itspm.ag/esentire-sorry4ek

Thanks to eSentire for supporting the conversation and helping us explore where AI meets security in the real world.

Sean Martin, CISSP & Marco Ciappelli
Co-Founders at ITSPmagazine

AI Coding Assistants Can be Both a Friend & a Foe

New research shows that GitLab's AI assistant, Duo, can be tricked into writing malicious code and even leaking private source data through hidden instructions embedded in developer content like merge requests and bug reports.

How? Through a classic prompt injection exploit that inserts secret commands into code that Duo reads. This results in Duo unknowingly outputting clickable malicious links or exposing confidential information.

While GitLab has taken steps to mitigate this, the takeaway is clear: AI assistants are now part of your attack surface. If you’re using tools like Duo, assume all inputs are untrusted, and rigorously review every output.

Read the details: https://arstechnica.com/security/2025/05/researchers-cause-gitlab-ai-developer-assistant-to-turn-safe-code-malicious/

A vulnerability in GitHub MCP lets malicious Issues hijack AI agents to leak data from private repos. Invariant calls this a “toxic agent flow” and shows it can exfiltrate sensitive info via prompt injection. GitHub alone can't fix it—mitigation needs system-level controls.

https://invariantlabs.ai/blog/mcp-github-vulnerability

At the recent #RSAC2025 conference, LMG Security's @sherridavidoff and @MDurrin drew packed crowds with their sessions on how hackers use AI to exploit stolen source code and a hands-on tabletop lab exploring deepfake cyber extortion.

We’ve received a lot of inquiries about these sessions! If you couldn’t attend RSA and you're interested in these topics, we also offer custom training and tabletop exercises to help your team prepare for the next generation of AI-powered cyber threats.

Contact us to learn more: https://www.lmgsecurity.com/contact-us/

AI-powered features are the new attack surface! Check out our new blog in which LMG Security’s Senior Penetration Tester Emily Gosney @baybedoll shares real-world strategies for testing AI-driven web apps against the latest prompt injection threats.

From content smuggling to prompt splitting, attackers are using natural language to manipulate AI systems. Learn the top techniques—and why your web app pen test must include prompt injection testing to defend against today’s AI-driven threats.

Read now: https://www.lmgsecurity.com/are-your-ai-backed-web-apps-secure-why-prompt-injection-testing-belongs-in-every-web-app-pen-test/

Ever wondered what really makes those powerful AI language models tick? Andrej Karpathy offers a clear explanation, revealing the secrets behind their training and architecture. Discover how they're evolving and the key security hurdles we need to overcome. A must-read for anyone curious about the behind-the-scene aspects AI! https://www.alanbonnici.com/2025/05/demystifying-llms-with-andrej-karpathy.html #ArtificialIntelligence #NLP #LanguageModels #AISecurity #TechInsights #FutureofAI #TTMO

Check out TechSpot’s new article featuring LMG Security’s @sherridavidoff and @MDurrin on how “Evil AI” is accelerating cyber threats.

The article recaps their #RSAC2025 presentation, where they demonstrated how rogue AI tools like WormGPT—AI stripped of ethical guardrails—can rapidly detect and help exploit real-world vulnerabilities.

From identifying SQL flaws to delivering working Log4j and Magento exploits, Sherri and Matt reveal how AI is arming cybercriminals faster than traditional defenses can keep up.

Read the full TechSpot article: https://www.techspot.com/news/107786-rsa-conference-experts-reveal-how-evil-ai-changing.html#commentsOffset

Microsoft Copilot for SharePoint just made recon a whole lot easier.   Read it here: www.pentestpartners.com/security-blo... #RedTeam #OffSec #AIsecurity #Microsoft365 #SharePoint #MicrosoftCopilot #InfoSec #CloudSecurity

The Dark Side of Multimodal AI: Unveiling New Security Risks

As multimodal AI systems evolve, they bring not only groundbreaking capabilities but also unprecedented safety risks. Recent findings reveal alarming vulnerabilities in these models that can be exploi...

https://news.lavx.hu/article/the-dark-side-of-multimodal-ai-unveiling-new-security-risks

Microsoft Copilot for SharePoint just made recon a whole lot easier.
 
One of our Red Teamers came across a massive SharePoint, too much to explore manually. So, with some careful prompting, they asked Copilot to do the heavy lifting...
 
It opened the door to credentials, internal docs, and more.
 
All without triggering access logs or alerts.
 
Copilot is being rolled out across Microsoft 365 environments, often without teams realising Default Agents are already active.
 
That’s a problem.
 
Jack, our Head of Red Team, breaks it down in our latest blog post, including what you can do to prevent it from happening in your environment.
 
Read it here: https://www.pentestpartners.com/security-blog/exploiting-copilot-ai-for-sharepoint/

AI-powered bots are shaping online conversations like never before: 100+ fake political personas used AI to spread targeted narratives undetected using Claude. #AISecurity #SocialMediaIntegrity #Disinformation | Read the full article - https://zurl.co/N2duK