BEGIN:VCALENDAR
VERSION:2.0
PRODID:Data::ICal 0.24
BEGIN:VEVENT
DESCRIPTION:   'Title: Pinchy Gets Played: How We Red-Teamed AI Agents Befo
 re the\n   Threats Did\n   Tags: Cloud Village | Creator Talk/Panel\n   Wh
 en: Saturday\, Aug 8\, 12:20 - 12:59 PDT\n   Where: LVCCW Level 3 W313 (Cl
 oud Village Talks) - [1]Map\n\n   Description:\n\n   AI agents are showing
  up in cloud workflows with credentials\,\n   autonomy\, and trust\, but s
 o are the threats targeting them. So\, before\n   attackers started probin
 g them\, Varonis Threat Labs did. We built a\n   target agent named Pinchy
  on the OpenClaw platform and put it through\n   a red-team gauntlet using
  well-known techniques. Pinchy handled\n   sophisticated technical attacks
  with ease but folded immediately\n   against simple social ones. The same
  drive to be useful turns these\n   agents into an attack surface that req
 uires entirely different\n   defensive strategies. Join us for a deep dive
  on the new risks\n   autonomous AI brings to the cloud. You'll leave with
  a clearer picture\n   of where AI agents fail\, why the threat model is u
 nlike anything that\n   came before it\, and what architectural controls â
 €” not prompts\, not\n   policies — actually keep environments secure.\n
 \n   SpeakerBio:  Doron Kapah\n\n   Doron is an experienced security resea
 rcher at Varonis Threat Labs. He\n   primarily focuses on advanced threat 
 detection capabilities\, threat\n   hunting\, and AI and cloud security. D
 oron also has extensive\n   experience in building innovative cybersecurit
 y product solutions\,\n   CTFs and has authored multiple publications in b
 oth state-sponsored\n   and cybercrime threat intelligence domains.\n\n   
 '\n\n   1. #LVCCW_Level3_South\n\n\n
DTEND:20260808T195900Z
DTSTART:20260808T192000Z
LOCATION:Cloud Village - LVCCW Level 3 W313 (Cloud Village Talks)
SUMMARY:Pinchy Gets Played: How We Red-Teamed AI Agents Before the Threats 
 Did
END:VEVENT
END:VCALENDAR