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=user_
 webcast_register&utm_medium=calendar&utm_source=brighttalk-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=user_webcast_register&utm_medium=calendar&utm
 _source=brighttalk-transact\n\nPresenter: Sonya Moisset, Staff AI Secu
 rity Advocate, Snyk\n\nWhen a developer installs an AI agent skill, th
 ey are making a trust decision they almost certainly do not know they 
 are making. Snyk’s ToxicSkills research into 3,000+ skills from ClawHu
 b and skills.sh found that 36% contain security flaws and 13% contain 
 critical issues, including credential theft, backdoor installation, an
 d active prompt injection payloads. And 91% of confirmed malicious ski
 lls combine traditional malware with prompt injection in a single arti
 fact.\n\nThis is not a theoretical risk. This is a supply chain that i
 s already under active exploitation. In this session, we’ll examine th
 ree documented attack chains and define what a rigorous 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 mo
 tivate risks in the AI skill supply chain \n• Actionable strategies to
  defend the agentic action layer
SEQUENCE:1778715008
END:VEVENT
END:VCALENDAR