Security | Threat Detection | Cyberattacks | DevSecOps | Compliance

Episode 13 - Battle-Hardened Research: Navigating the Intersection of AI and Open Source

Richard Bejtlich sits down with Ali Islam to pull back the curtain on how a security research lab functions within a modern security company. Moving beyond the "ivory tower" of academia, Ali explains why researchers must be battle-hardened by real-world threat actor techniques to remain effective in the field. The conversation dives into Corelight’s unique commitment to the open source community through the direct funding of Zeek and Suricata developers, ensuring that community-driven tools can scale to meet massive enterprise traffic demands.

Detecting Threats in Multi-Agent Orchestration Systems: LangChain, CrewAI, and AutoGPT

It’s Tuesday morning at a mid-size fintech. A customer-support workflow runs on CrewAI in production: a Triage agent reads tickets, a Records agent pulls customer history, a Remediation agent drafts and sends the reply. A user submits a ticket with a pasted error log containing an indirect prompt injection. Triage summarizes and delegates. Records, interpreting instructions embedded in the summary, pulls 2,400 customer records instead of one.