Archive

Exhibit & Exploit: Two DEF CON 33 Highlights from the Past & Future of Hacking

Humans, hacker culture and AI: Notes from Hacker Summer Camp

Avishai Efrat

Security research

Prompt Mines: 0-Click Data Corruption In Salesforce Einstein

Aug 14, 2025

•

17 min read

Prompt Mines: 0-Click Data Corruption In Salesforce Einstein

Tamir Ishay Sharbat

Security research

Aug 7, 2025

•

7 min read

AgentFlayer: Minimum Clicks, Maximum Leaks: Tilling ChatGPT’s Attack Surface

Exploiting ChatGPT with Language Alone: A Deep Dive into 0Click and 1Click Attacks.

Dmitry Lozovoy

Security research

Aug 6, 2025

•

11 min read

AgentFlayer: ChatGPT Connectors 0click Attack

Tamir Ishay Sharbat

AI Enterprise Compromise - 0click Exploit Methods

Aug 6, 2025

•

2 min read

AI Enterprise Compromise - 0click Exploit Methods

Michael Bargury

Security research

Aug 1, 2025

•

10 min read

AgentFlayer: When a Jira Ticket Can Steal Your Secrets

TL;DR: A 0click attack through a malicious Jira ticket can cause Cursor to exfiltrate secrets from the repository or local file system.

Marina Simakov

Why Aren’t We Making Any Progress In Security From AI

Jul 31, 2025

•

9 min read

Why Aren’t We Making Any Progress In Security From AI

Guardrails Are Soft Boundaries. Hard Boundaries Do Exist.

Michael Bargury

Reconstructing a timeline for Amazon Q prompt infection

Jul 30, 2025

•

8 min read

Reconstructing a timeline for Amazon Q prompt infection

How a rogue GitHub commit, automation missteps, and a deceptive AI assistant led to one of the most bizarre prompt injection cases in recent memory.

Michael Bargury

Security research

Jul 7, 2025

•

9 min read

AgentFlayer: When AIjacking Leads to Full Data Exfiltration in Copilot Studio

Tamir Ishay Sharbat

I Just Wanted to Take a Note — and Your Token Came Along

Jul 3, 2025

•

11 min read

I Just Wanted to Take a Note — and Your Token Came Along

Dmitry Lozovoy

Security research

EchoLeak: A Reminder That AI Agent Risks Are Here to Stay

Jun 20, 2025

•

7 min read

EchoLeak: A Reminder That AI Agent Risks Are Here to Stay

Marina Simakov

Security research

Jun 11, 2025

•

9 min read

AgentFlayer: Discovery Phase of AI Agents in Copilot Studio

Tamir Ishay Sharbat

1 2 3 4 5 6 7

Exhibit & Exploit: Two DEF CON 33 Highlights from the Past & Future of Hacking

Prompt Mines: 0-Click Data Corruption In Salesforce Einstein

AgentFlayer: Minimum Clicks, Maximum Leaks: Tilling ChatGPT’s Attack Surface

AgentFlayer: ChatGPT Connectors 0click Attack

AI Enterprise Compromise - 0click Exploit Methods

AgentFlayer: When a Jira Ticket Can Steal Your Secrets

Why Aren’t We Making Any Progress In Security From AI

Reconstructing a timeline for Amazon Q prompt infection

AgentFlayer: When AIjacking Leads to Full Data Exfiltration in Copilot Studio

I Just Wanted to Take a Note — and Your Token Came Along

EchoLeak: A Reminder That AI Agent Risks Are Here to Stay

AgentFlayer: Discovery Phase of AI Agents in Copilot Studio

Zenity Labs

Home

Meet Us

Join Us