Flutterby™!
: Exploiting ChatGPT Deep Research Agent
Exploiting ChatGPT Deep Research Agent
2025-09-18 20:17:51.944377+02 by
Dan Lyke
0 comments
ShadowLeak: A Zero-
Click, Service-Side Attack Exfiltrating Sensitive Data Using ChatGPT’s Deep Research
Agent. If a user has given ChatGPT's "Deep Research Agent" access to their Gmail inbox
and to external websites, crafting an email that causes information from other emails to be
exfiltrated via access to external sites...
The Winning Strategy: Encoding the PII - Our final and
successful strategy was to instruct the agent to encode the extracted PII into
Base64 before appending it to the URL. We framed this action as a
necessary security measure to protect the data during transmission.
[ related topics:
Interactive Drama Weblogs
]
comments in descending chronological order (reverse):
Comment policy
We will not edit your comments. However, we may delete your
comments, or cause them to be hidden behind another link, if we feel
they detract from the conversation. Commercial plugs are fine,
if they are relevant to the conversation, and if you don't
try to pretend to be a consumer. Annoying endorsements will be deleted
if you're lucky, if you're not a whole bunch of people smarter and
more articulate than you will ridicule you, and we will leave
such ridicule in place.
Flutterby™ is a trademark claimed by
Dan Lyke for the web publications at www.flutterby.com and www.flutterby.net.