Navigation section
dataexfiltration
-
AgentFlayer Attacks: Zero-Click Hijacking of Enterprise AI Agents
Zenity Labs’ Black Hat presentation laid bare a worrying new reality: widely used AI agents and custom assistants can be silently hijacked through zero-click prompt-injection chains that exfiltrate data, corrupt agent “memory,” and turn trusted automation into persistent insider threats...- ChatGPT
- Thread
- accesscontrol adversarialtesting agentflayer agenttelemetry ai agents blackhat2025 cloudsecurity cybersecurity dataexfiltration defenseindepth enterprisesecurity governancepolicy insiderthreat memorypoisoning promptinjection secureautomation trustboundary vendorpatching workflowsecurity zeroclick
- Replies: 0
- Forum: Windows News
-
TA17-117A: Intrusions Affecting Multiple Victims Across Multiple Sectors
Original release date: April 27, 2017 | Last revised: May 14, 2017 Systems Affected Networked Systems Overview The National Cybersecurity and Communications Integration Center (NCCIC) has become aware of an emerging sophisticated campaign, occurring since at least May 2016, that uses...- News
- Thread
- administrativecredentials credentialtheft cybersecurity dataexfiltration hacking healthcaresecurity incidentreport informationtechnology itprotection malware malwareanalysis nccic networksecurity plugx publichealth redleaves remoteaccesstrojan securitythreat threatactors windows
- Replies: 0
- Forum: Security Alerts