Security Intelligence Promptware, cloud security trends for 2026, and what the Xbox One hack means for cybersecurity
Mar 25, 2026
Kimmie Farrington, a security detection engineer focused on telemetry and IAM; Seth Glasgow, a cyber range advisor on incident response and cloud tradecraft; and Ian Molloy, a security research lead in offensive and defensive analysis. They cover promptware and expanding the LLM attack kill chain. They unpack cloud attacks targeting ecosystems, ransomware living off the land, OT’s aging risks, and the Xbox One hardware breach.
AI Snips
Chapters
Transcript
Episode notes
Indirect Prompt Injection Enables Mass Amplification
- Indirect prompt injections let attackers seed documents that compromise models at scale without repeated interaction.
- One compromise can amplify across models and agents, enabling fast automated reconnaissance and pivoting.
Log AI Conversations And Lock Agent Identities
- Improve telemetry and logging of model inputs and agent activity so defenders can see where injections occur.
- Lock down agent identities, track which model/version an agent uses, and enforce least privilege on agent accounts.
Cloud Attacks Target Ecosystems Not Infrastructure
- Attackers now target cloud ecosystems (identities, APIs, integrations) rather than core infrastructure, exploiting implicit trust between components.
- This makes breaches scalable: compromise one token or integration and pivot through federated services.