BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//pydata-amsterdam2026//talk//VVYGUQ
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-pydata-amsterdam2026-VVYGUQ@pretalx.com
DTSTART;TZID=CET:20260910T115500
DTEND;TZID=CET:20260910T122500
DESCRIPTION:Have you ever given an AI agent access to your codebase\, your 
 inbox\, or your files? The model is from a top lab\, the system prompt or 
 rules file says what it can and can't do. Do you... trust it? Or does it m
 ake you feel just a little bit uneasy?\n\nIf so\, you'd be right.\n\nIn th
 is talk\, we'll look at how AI agents fail: in everyday use\, and under de
 liberate attack. We'll explore why the safety layers most of us rely on ar
 e probabilistic rather than guaranteed\, what happens when someone exploit
 s that\, and what lessons we can draw from security engineering. You'll le
 ave with a better understanding of where agents are vulnerable\, and concr
 ete steps you can take to deploy them more safely.
DTSTAMP:20260710T141304Z
LOCATION:Main stage
SUMMARY:Is Your Agent as Secure as You Think? - Marysia Winkels
URL:https://pretalx.com/pydata-amsterdam2026/talk/VVYGUQ/
END:VEVENT
END:VCALENDAR