BEGIN:VCALENDAR
VERSION:2.0
X-WR-CALNAME:BrightTALK Event
PRODID:-//BrightTALK//NONSGML BrightTALK Event Calendar//EN
CALSCALE:GREGORIAN
METHOD:REQUEST
BEGIN:VEVENT
UID:https://www.brighttalk.com/webcast/18796/668352
DTSTAMP:20260512T141441Z
ORGANIZER:MAILTO:noreply@brighttalk.com
LOCATION:BrightTALK
URL:https://www.brighttalk.com/webcast/18796/668352?utm_campaign=commu
 nication_reminder_24hr_registrants&utm_medium=calendar&utm_source=brig
 httalk-transact
DTSTART:20260612T140000Z
DTEND:20260612T150000Z
SUMMARY:Live webcast: Toxic Flows: When Your Agent Skill Becomes a Sup
 ply Chain Attack
DESCRIPTION:Click here to attend: https://www.brighttalk.com/webcast/1
 8796/668352?utm_campaign=communication_reminder_24hr_registrants&utm_m
 edium=calendar&utm_source=brighttalk-transact\n\nPresenter: Sonya Mois
 set, Staff AI Security Advocate, Snyk\n\nWhen a developer installs an 
 AI agent skill, they are making a trust decision they almost certainly
  do not know they are making. Snyk’s ToxicSkills research into 3,000+ 
 skills from ClawHub and skills.sh found that 36% contain security flaw
 s and 13% contain critical issues, including credential theft, backdoo
 r installation, and active prompt injection payloads. And 91% of confi
 rmed malicious skills combine traditional malware with prompt injectio
 n in a single artifact.\n\nThis is not a theoretical risk. This is a s
 upply chain that is already under active exploitation. In this session
 , we’ll examine three documented attack chains and define what a rigor
 ous defense of the agentic action layer requires.\n\nWe’ll explore: \n
 • A deep dive into how malicious skills operate through recent attacks
  \n• Tactics to motivate risks in the AI skill supply chain \n• Action
 able strategies to defend the agentic action layer
SEQUENCE:1781185707
END:VEVENT
END:VCALENDAR