LogoZenity Labs
AI Agent Security Summit (On Demand)
Join Us
Authors
Subscribe
LogoZenity Labs

Archive

Security research

Sure, Let AI Browse the Internet—What Could Possibly Go Wrong?

Oct 7, 2024

•

3 min read

Sure, Let AI Browse the Internet—What Could Possibly Go Wrong?

Internet browsing for AI agents leads to 0click compromise but these mitigations can help

Michael Bargury
Michael Bargury

Security research

+1

TTPs.ai for GenAI-Targeted Attacks

Oct 2, 2024

•

4 min read

TTPs.ai for GenAI-Targeted Attacks

Guiding threat simulation and defense for Copilots and Agents

Michael Bargury
Michael Bargury

Security research

Over Permissions in Salesforce Einstein and Unexpected Consequences

Sep 30, 2024

•

9 min read

Over Permissions in Salesforce Einstein and Unexpected Consequences

Tamir Ishay Sharbat
Tamir Ishay Sharbat

Security research

Outsmarting Copilot: Creating Hyperlinks in Copilot 365

Sep 22, 2024

•

7 min read

Outsmarting Copilot: Creating Hyperlinks in Copilot 365

Dmitry Lozovoy
Dmitry Lozovoy

Security research

The Long and Winding Road of DLP Patches in Power Platform

Sep 17, 2024

•

8 min read

The Long and Winding Road of DLP Patches in Power Platform

Reviewing Microsoft's Fix for the 'All You Need Is Guest' DLP Bypass

Avishai Efrat
Avishai Efrat

Talks

+2

A Summary of Zenity Research Published at BlackHat 2024

Aug 19, 2024

•

4 min read

A Summary of Zenity Research Published at BlackHat 2024

New Attack Vectors Discovered for Initial Access and Post-Compromise

Michael Bargury
Michael Bargury

Talks

+1

Copilot Vulnerable to RCE: A New Attack Vector Into The Enterprise

Aug 14, 2024

•

19 min read

Copilot Vulnerable to RCE: A New Attack Vector Into The Enterprise

We Need To Address Promptware Now

Michael Bargury
Michael Bargury

Security research

Phantom References in Microsoft Copilot

Aug 11, 2024

•

5 min read

Phantom References in Microsoft Copilot

Tamir Ishay Sharbat
Gal Malka
Tamir Ishay Sharbat, +1

Talks

+2

Links and materials for Living off Microsoft Copilot

Aug 8, 2024

•

6 min read

Links and materials for Living off Microsoft Copilot

Links, source code, tools and slides for BlackHat USA 2024

Michael Bargury
Michael Bargury

Security research

Indirect Prompt Injection: Advanced Manipulation Techniques

Aug 7, 2024

•

7 min read

Indirect Prompt Injection: Advanced Manipulation Techniques

Tamir Ishay Sharbat
Tamir Ishay Sharbat

Talks

+2

Links and materials for 15 Ways to Break Your Copilot

Aug 7, 2024

•

4 min read

Links and materials for 15 Ways to Break Your Copilot

Links, source code, tools and slides for BlackHat USA 2024

Michael Bargury
Michael Bargury
Indirect Prompt Injection: From Initial Success to Robustness

Aug 6, 2024

•

12 min read

Indirect Prompt Injection: From Initial Success to Robustness

Tamir Ishay Sharbat
Tamir Ishay Sharbat
1...4567
Zenity Labs

Zenity Labs

Latest research, tools and talks about breaking and building AI systems, agents and assistants


Home

Meet Us

Join Us

© 2026 Zenity Labs.
beehiivPowered by beehiiv