Live
Zenity's Real-Time Agent Security Hits Azure Marketplace Preview for Copilot Studio·MSFT +0.1%Microsoft Copilot's Policy Flaw Allows Blocked AI Agents to Resurface, Creating Governance and Audit Nightmares·NVDA +3.0%Microsoft Silently Patches Copilot Audit Blind Spot That Allowed Silent Data Exfiltration·GOOGL +1.2%Microsoft Quietly Patches Copilot Audit-Log Bypass, Keeps Customers in the Dark·AMZN +2.9%Microsoft 365 Copilot’s Missing Audit Logs: The Hidden Risk Behind Zero-Click Data Leaks·MSFT +0.1%Leading GenAI Browser Assistants Found Hoovering Up Social Security Numbers, Medical Data Without Consent·NVDA +3.0%Zenity Labs Unveils AgentFlayer: Zero-Click Exploits Hijack ChatGPT, Microsoft Copilot, and Salesforce Einstein·GOOGL +1.2%Patch Now: AVEVA PI Integrator Vulnerabilities Could Let Attackers Hijack OT Analytics·AMZN +2.9%Zenity's Real-Time Agent Security Hits Azure Marketplace Preview for Copilot Studio·MSFT +0.1%Microsoft Copilot's Policy Flaw Allows Blocked AI Agents to Resurface, Creating Governance and Audit Nightmares·NVDA +3.0%Microsoft Silently Patches Copilot Audit Blind Spot That Allowed Silent Data Exfiltration·GOOGL +1.2%Microsoft Quietly Patches Copilot Audit-Log Bypass, Keeps Customers in the Dark·AMZN +2.9%Microsoft 365 Copilot’s Missing Audit Logs: The Hidden Risk Behind Zero-Click Data Leaks·MSFT +0.1%Leading GenAI Browser Assistants Found Hoovering Up Social Security Numbers, Medical Data Without Consent·NVDA +3.0%Zenity Labs Unveils AgentFlayer: Zero-Click Exploits Hijack ChatGPT, Microsoft Copilot, and Salesforce Einstein·GOOGL +1.2%Patch Now: AVEVA PI Integrator Vulnerabilities Could Let Attackers Hijack OT Analytics·AMZN +2.9%

Data Exfiltration

The latest Data Exfiltration coverage — news, analysis, and updates from the WindowsNews.AI desk.

12 stories in view AI assisted desk updated 6:01 AM
Latest Most Read Breaking
Sort
Agent Security · Ai Security

Zenity's Real-Time Agent Security Hits Azure Marketplace Preview for Copilot Studio

Microsoft Copilot Studio agents now have a dedicated inline security layer that can block prompt injections, data exfiltration, and secrets misuse mid-execution, following Zenity’s expanded...

Advertisement
Ai Governance · Audit Logs

Microsoft 365 Copilot’s Missing Audit Logs: The Hidden Risk Behind Zero-Click Data Leaks

When Microsoft patched CVE-2025-32711 in June 2025, it closed a critical zero-click vulnerability that allowed attackers to silently siphon sensitive data through Microsoft 365 Copilot. Dubbed...

AI AI & Copilot Desk·47w ago
Ai Browser · Auditing

Leading GenAI Browser Assistants Found Hoovering Up Social Security Numbers, Medical Data Without Consent

A sweeping new audit of the most popular generative AI browser assistants reveals that several widely used extensions silently capture and transmit highly sensitive information from ordinary web...

AI AI & Copilot Desk·48w ago
Agentflayer · Ai Security

Zenity Labs Unveils AgentFlayer: Zero-Click Exploits Hijack ChatGPT, Microsoft Copilot, and Salesforce Einstein

Zenity Labs has dropped a bombshell at Black Hat USA 2025: a new attack framework called AgentFlayer that lets adversaries silently hijack enterprise AI agents without so much as a mouse click....

AI AI & Copilot Desk·48w ago
Aveva Pi Integrator · Cisa Icsa-25-224-04

Patch Now: AVEVA PI Integrator Vulnerabilities Could Let Attackers Hijack OT Analytics

On August 12, 2025, the U.S. Cybersecurity and Infrastructure Security Agency (CISA) published an industrial control systems (ICS) advisory warning of two high-severity vulnerabilities in AVEVA’s...

SE Security Desk·48w ago
Access Control · Adversarial Testing

AgentFlayer Unleashed: Zero-Click Chains Turn Enterprise AI Agents into Stealth Insider Threats

At Black Hat USA 2025, Zenity Labs peeled back the curtain on a threat that security teams have long feared but rarely seen weaponized at scale: zero-click prompt injection attacks that silently...

AI AI & Copilot Desk·48w ago
Agentflayer · Ai Autonomous Threats

Zenity Labs’ AgentFlayer Exposes Zero-Click Exploits: Microsoft Copilot, ChatGPT AI Agents Hijacked Without User Action

At Black Hat USA 2025, security researchers from Zenity Labs pulled back the curtain on a dangerously overlooked attack surface: enterprise AI agents that can be silently hijacked with zero user...

AI AI & Copilot Desk·49w ago
Ai · Ai Risks

Black Hat 2025: Zero-Click Exploits Can Hijack ChatGPT, Copilot, and Einstein Without a Trace

Security researchers at Zenity Labs have dropped a bombshell at Black Hat USA 2025: a new breed of zero-click exploit chains can silently hijack enterprise AI agents, including OpenAI’s ChatGPT,...

AI AI & Copilot Desk·49w ago
Adversarial Attacks · Ai Ethics

EchoLeak and the Rising Threat of Zero-Click Prompt Injection in Microsoft Copilot

Large language models (LLMs) like Microsoft Copilot are revolutionizing enterprise productivity, but their integration into critical workflows has introduced an entirely new and rapidly evolving...

AI AI & Copilot Desk·50w ago