BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//cfp.troopers.de//tr26-cfp//speaker//PEWRAE
BEGIN:VTIMEZONE
TZID:CET
BEGIN:STANDARD
DTSTART:20001029T040000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000326T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-tr26-cfp-RVTUNU@cfp.troopers.de
DTSTART;TZID=CET:20260624T174500
DTEND;TZID=CET:20260624T181500
DESCRIPTION:AI coding agents have significantly changed the world of code d
 evelopment. Smarter\, faster\, and more skilled\, they gain greater autono
 my and trust.  Isn’t that too good to be true\, and we might be dealing 
 with a double-edged sword here? Can attackers use the same capabilities of
  the AI agents to attack their own users?  And most importantly: what’s 
 the worst that could happen if you fully trust some random AI Agent?\nIn t
 his talk I demonstrate how remote attackers exploit vulnerabilities in pop
 ular AI coding agents to capture sensitive data and compromise the compute
 rs of their users.  Additionally\, I conclude with recommendations for use
 rs and developers on how to mitigate such attacks.
DTSTAMP:20260627T175913Z
LOCATION:Track 3
SUMMARY:My AI agent mesmerized\, but got me compromised - Ahmad Abolhadid
URL:https://cfp.troopers.de/tr26-cfp/talk/RVTUNU/
END:VEVENT
END:VCALENDAR