Arrêtez d’utiliser ChatGPT si vous ne savez pas encore ce qu’est le ShadowLeak intelligence-artificielle.com/arretez-duti...

⚠️ un email invisible peut déclencher ChatGPT pour voler vos données... sans clic ni alerte.
Stop à l’utilisation non informée.

#Cybersécurité #ShadowLeak #InnovationIA

ShadowLeak Explained: Zero-Click, Server-Side Agent Exfiltration (and how it differs from EchoLeak) ShadowLeak is the kind of AI security story that makes defenders rethink assumptions. In mid-Sept...

#indirect-prompt-injection #email-security #shadowleak #ai-security

Origin | Interest | Match

ShadowLeak Explained: Zero-Click, Server-Side Agent Exfiltration (and how it differs from EchoLeak) ShadowLeak is the kind of AI security story that makes defenders rethink assumptions. In mid-September 2025, researchers disclosed a…

ShadowLeak Explained: Zero-Click, Server-Side Agent Exfiltration (and how it differs from EchoLeak) ShadowLeak is the kind of AI security story that makes defenders rethink assumptions. In mid-Sept...

#indirect-prompt-injection #email-security #shadowleak #ai-security

Origin | Interest | Match

Original post on mastodon.online

#KIMissbrauch

Ein gezielter Angriff namens #ShadowLeak zeigte, wie Angreifer #ChatGPT über manipulierte E-Mails zur Preisgabe personenbezogener Daten bringen konnten.

Die Schwachstelle trat auf, wenn Nutzer dem KI-Agenten Zugriff auf externe Konten wie #E-Mail-Postfächer gewährten.

OpenAI […]

InfoSec News Nuggets 9/24/2025

InfoSec News Nuggets 9/24/2025 Is Big Tech Doing Enough to Fight Scams? The EU Isn’t So Sure As online scammers continue to harass consumers, the European Union is investigating whether major c...

#InfoSec #News #Nuggets #AboutDFIR #news #nuggets #pypi #ShadowLeak

Origin | Interest | Match

ChatGPT faces zero-click server-side flaw, risks data theft

Security researchers found ShadowLeak, a zero‑click, server‑side exploit in ChatGPT’s Deep Research agent that can exfiltrate data via a crafted email without user interaction. Read more: getnews.me/chatgpt-faces-zero-click... #shadowleak #chatgpt #zeroclick

ShadowLeak Exploit Exposed Gmail Data Through ChatGPT Agent Follow us on Bluesky, Twitter (X), Mastodon and Facebook at @Hackread

A service-side flaw in OpenAI's ChatGPT, known as the #ShadowLeak attack, used indirect prompt injection to leak Gmail data.

Read: hackread.com/shadowleak-e...

#CyberSecurity #ChatGPT #OpenAI #Gmail #InfoSec #AI #Vulnerability

Zero-Click ChatGPT Vulnerability Exposes Gmail Data Without User Knowledge | Security Land Critical ShadowLeak vulnerability in ChatGPT's Deep Research agent allows hackers to steal Gmail data without user interaction.

A security flaw has been discovered in ChatGPT that could silently steal your Gmail data without you ever knowing. Security firm Radware has uncovered what they’re calling “ShadowLeak”.

#SecurityLand #CyberWatch #ChatGPT #Vulnerability #ShadowLeak

Read More: www.security.land/zero-click-c...

CISA avvisa su malware Ivanti EPMM e nove ICS advisories; OpenAI corregge ShadowLeak che espone dati da tool AI integrati.

#ApacheTomcat #cisa #ICS #Ivanti #ShadowLeak
www.matricedigitale.it/2025/09/19/i...

🚨 ShadowLeak exposed @ChatGPT’s Deep Research to zero-click data theft.
⚠️ Exploited OpenAI servers
⚠️ Bypassed safeguards with clever prompts
⚠️ Left almost no traces
✅ Patched by @OpenAI, but experts warn of broader AI attack surfaces.

#AIsecurity #ChatGPT #ShadowLeak #CyberSecurity