BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//programme.europython.eu//europython-2026//speaker//3VHXX
 W
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-europython-2026-TUKAYS@programme.europython.eu
DTSTART;TZID=CET:20260716T151000
DTEND;TZID=CET:20260716T154000
DESCRIPTION:AI agents are no longer just generating text\, they are reading
  PDFs\, scraping websites\, calling APIs\, and taking autonomous actions i
 nside our Python applications. But what happens when the documents they re
 ad are malicious?\n\nIn this talk\, we’ll explore indirect prompt inject
 ion\, a subtle but major attack where hidden instructions embedded in PDFs
 \, HTML pages\, or external data sources hijack an AI system’s behavior.
  Unlike classic prompt injection\, this attack doesn’t come from the use
 r\, it comes from the data your Python pipeline trusts.
DTSTAMP:20260708T213947Z
LOCATION:S4
SUMMARY:Hunting the Invisible: Indirect Prompt Injection in Python Pipeline
 s - John Robert
URL:https://programme.europython.eu/europython-2026/talk/TUKAYS/
END:VEVENT
END:VCALENDAR