BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//cfp.securityfest.com//2026//speaker//UQKDZT
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-2026-L38XLJ@cfp.securityfest.com
DTSTART;TZID=CET:20260528T093000
DTEND;TZID=CET:20260528T101500
DESCRIPTION:Everyone is diving headfirst into the AI pool. The problem is t
 hey're diving into the shallow end. LLMs are being packed into every nook 
 and crannie\, mostly places nobody wanted it or asked for it. I'm going to
  be taking a baseball bat to LLMs - their hallucinatory nature and the ext
 ra instructions we're saddled with we don't get to see.. I'll be showing l
 ogs of how they literally talk themselves into lying to you. It's bad. Bri
 ng a helmet. Prompt engineering has become harness engineering\, and now i
 ts "memory and context engineering". Openclaw and now codex are storing lo
 cal files and 'memories' to try and handle the 'context window problem'. M
 oltbook has 3 million 'agents'. Openclaw is being used as a c2 now. TeamPC
 P is infecting every npm package they can with backdoors - weekly at this 
 point! Just in 2026 alone we have more than tripled the number of supply c
 hain bugs in tooling used in the LLM landscape The attack surface is growi
 ng so rapidly we can barely keep track of it. This talk will explore all t
 his new attack surface\, and cover some of the things you can do about it\
 , and how to avoid the landmines and pitfalls when using LLMs.
DTSTAMP:20260625T173040Z
LOCATION:Main Stage
SUMMARY:Claude is your insider threat now - Dan Tentler
URL:https://cfp.securityfest.com/2026/talk/L38XLJ/
END:VEVENT
END:VCALENDAR