As browsers evolve from passive tools into active agents, they are becoming a new enterprise attack surface." In this BlueHat 2026 talk, Dana Baril, Principal Security Researcher at Microsoft, shares how agentic browsers are reshaping the security landscape by taking actions on behalf of users and how attackers are already adapting to take advantage of these capabilities. Through real-world research, demonstrations, and threat intelligence, Dana examines emerging risks including prompt injection, credential theft, malicious browser extensions, unauthorized actions, and data exfiltration. The session also highlights observed threats targeting AI-powered browsing experiences, including campaigns affecting thousands of organizations and the growing focus on AI-generated data and conversation histories as a target. Key takeaways: ➤Why agentic browsers introduce risks beyond traditional browser security ➤How attackers are targeting AI-powered browsing experiences today ➤What makes detecting malicious AI browser activity so challenging ➤How contextual behavioral detection can help identify suspicious agent actions at scale Watch the session and explore the slides to learn why securing agentic browsers is becoming an urgent priority for enterprise defenders: https://lnkd.in/exgwQKde
Microsoft Security Response Center
Computer and Network Security
Protecting customers and Microsoft from current and emerging threats related to security and privacy.
About us
The Microsoft Security Response Center (MSRC) is dedicated to safeguarding customers and Microsoft from security threats. With over two decades of experience, we focus on prevention, rapid defense, and community trust. Together, we’ll continue to protect our users and the broader ecosystem.
- Website
-
https://www.microsoft.com/en-us/msrc
External link for Microsoft Security Response Center
- Industry
- Computer and Network Security
- Company size
- 10,001+ employees
- Specialties
- Cybersecurity, Security response, Incident response, Bug bounty, Security research, and BlueHat
Updates
-
At BlueHat Asia, Haakon Wik Gulbrandsrud of Binary Security AS will share how a year-long research project led to the discovery and responsible disclosure of multiple critical cross-tenant vulnerabilities in Azure. In this talk, Haakon will walk through the methodology behind the research, from reverse engineering and architectural analysis to identifying the shared root cause that enabled full cross-tenant compromise. He'll discuss the challenges of uncovering complex cloud vulnerabilities, the process of validating and reporting the findings, and the lessons learned along the way. Haakon will also briefly reflect on the role AI played during the research process, including where it proved useful and where its limitations became apparent.
-
-
⏰ Final reminder: Registration for BlueHat Asia closes tonight at 11:59 PM. Secure your spot before registration closes: https://aka.ms/bluehatreg
BlueHat Asia is heading to Singapore on September 17–18! 👉Apply now for your chance to join us: https://aka.ms/bluehatreg Applications close July 17. #BlueHat
-
-
What happens when small identity weaknesses turn into full account compromise? Join Felix Boulet, Microsoft 2026 Microsoft Most Valuable Researcher (MVR) and Zero Day Quest qualifier, and Callum Carney, Senior Security Researcher at Microsoft, at BlueHat Asia as they discuss four real-world Entra ID findings that challenge common assumptions about MFA, Conditional Access, and identity security. From reclaiming stale accounts to bypasses that leverage state reuse, parsing quirks, and unexpected feature interactions, this session shows how seemingly minor issues can create powerful attack paths. Along the way, attendees will get a rare dual perspective: Felix will share how the vulnerabilities were discovered, while Callum will provide insight into Microsoft's assessment process, remediation efforts, and the lessons learned that help strengthen security across the ecosystem. Want to hear Felix and Callum share the story behind these discoveries? Join us at BlueHat Asia. Registration closes July 17. Register today at aka.ms/bluehatreg.
-
-
Congratulations to all the researchers recognized in the MSRC 2026 Q2 Security Researcher Leaderboard! This quarter marks the final quarterly points-based leaderboard as we continue the evolution of our researcher recognition program. We are grateful to every researcher who partnered with us and helped strengthen the security of Microsoft products and services through their hard work and dedication. We’d also like to recognize the top 10 researchers in this quarter’s leaderboard for their outstanding contributions. Thank you for helping protect customers around the world. 🥇Asaf Cohen (XBREACH.AI) 🥈C46F3708A45EF0041BD0A49DDAEA0E25 🥉Ron 4. Thanatos Tian (HKPolyU) & wgg & 2st with Diffract 5. haowei yan 6. fce141fd6b42fcec05c1285b15d8f999 7. Ofek Levin 8. pwn2addr 9. Kim Seung Chan (@mylostchristmas) 10. Jianyang Song Learn more and view the full leaderboard: https://lnkd.in/e5RaKtwz
-
-
Security updates for July 2026 are now available. Details are here: https://msft.it/6018SZEg0
-
-
Today, we're proud to recognize the Top 100 Microsoft 2026 Most Valuable Researchers (MVRs). Security researchers play a critical role in helping protect customers by identifying and reporting vulnerabilities across Microsoft products and services. We're grateful for their partnership and the impact they have made over the past year. Congratulations to this year's Top 10 MVRs: 🥇C46F3708A45EF0041BD0A49DDAEA0E25 🥈ShinHyuiq & Alan Pang 🥉cherrypick 4. Brad Schlintz (nmdhkr) 5. wtm 6. Asaf Cohen (XBREACH.AI) 7. bccc95a61a3cc79d7b2c4423c808f744 8. Felix B. 9. 142a423e2574abf10d65eba46891ca5e 9. Anonymous This year, we updated the MVR leaderboard to rank researchers based on total bounty awards, creating a clearer connection between recognition and security impact. We also introduced Special Mentions to recognize researchers who submitted valid vulnerability reports during the recognition period, regardless of leaderboard ranking. See our blog for the complete list of the Top 100 MSRC 2026 Most Valuable Researchers and the top researchers by bounty program: https://lnkd.in/e4GTzaQT Thank you to every researcher who partnered with us this year to help protect customers worldwide.
-
-
What drives a successful security researcher? In our latest spotlight, Microsoft Most Valuable Researcher (MVR) and Zero Day Quest Qualifier Matthew Jensen shares how curiosity, persistence, and a hands-on approach led him from exploring technology on his own to becoming a respected Azure security researcher. Learn how he approaches cloud security research, validates fixes, and helps improve Azure security through vulnerability research. Read his story in our latest blog post: https://lnkd.in/eSZBfcSZ
-
-
Agentic AI attacks don't need to break the model. They exploit the architecture. In this BlueHat session, Pete Bryan, Principal AI Security Researcher with Microsoft's AI Red Team (AIRT), shares lessons from a year of hands-on red teaming against real-world agentic AI systems. Drawing on operational evidence, Pete introduces an updated taxonomy of agentic AI failure modes and examines how the threat landscape is evolving as agents gain access to tools, memory, MCP integrations, and computer-use capabilities. The talk discusses seven newly identified failure modes, including goal hijacking, agentic supply chain compromise, inter-agent trust escalation, session context contamination, MCP/plugin abuse, and capability disclosure. Pete explains how seemingly small weaknesses can be chained together to create significant security impact. Using real-world case studies from Microsoft AI Red Team engagements, Pete demonstrates how attackers can: 🔹 Manipulate memory systems to persist malicious influence 🔹 Exfiltrate sensitive data through agent capabilities 🔹 Bypass human-in-the-loop controls 🔹 Exploit inconsistent guardrails across agent workflows 🔹 Leverage capability disclosure to develop more targeted attacks The talk also examines why traditional approaches to AI security are falling short. Across engagements, the team repeatedly observed human-in-the-loop controls being bypassed, guardrail inconsistencies creating attack opportunities, and probabilistic controls failing to provide reliable protection. 📺 Watch the full session on YouTube: https://lnkd.in/ecGeJVvw 📖 Explore the agentic AI failure modes taxonomy: https://lnkd.in/eVg_fymM ⬇️ View the slides below
-
How does a standard user become a global admin? At BlueHat 2026, Dylan Ryan-Zilavy, independent security researcher and Microsoft Most Valuable Researcher (MVR), and Cameron Vincent, Senior Security Researcher at Microsoft Security Response Center (MSRC), walk through a real-world vulnerability that enabled privilege escalation from a low-privileged user to Global Administrator in Microsoft Entra. The presentation follows Dylan's research journey, from exploring how application identities authenticate in Entra and questioning assumptions about OAuth token validation, to discovering a novel attack path involving audience validation and application identifier URIs. Along the way, he shares the persistence, dead ends, and creative thinking that ultimately led to the finding. The session also provides an inside look at Microsoft's response, including how the report was triaged, reproduced, and ultimately fixed. Cameron shares lessons from the investigation, guidance on secure token validation, and best practices for building identity-aware applications. Watch the session recording on YouTube: https://lnkd.in/dnnEMVBc The presentation slides are included with this post for anyone who would like to follow along or dive deeper into the research.