<![CDATA[Offensive Engineering: Live Sessions]]>https://offensive.infosecrelations.com/s/live-sessionshttps://substackcdn.com/image/fetch/$s_!PLlt!,w_256,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F9fd8bd9b-6699-4e30-8062-980e60019033_1068x1068.pngOffensive Engineering: Live Sessionshttps://offensive.infosecrelations.com/s/live-sessionsSubstackSun, 28 Jun 2026 03:25:21 GMT<![CDATA[Live Sessions #2 Securing Autonomous Agents Against Data Leakage with Mahesh Kumar Goyal]]>https://offensive.infosecrelations.com/p/live-sessions-2-securing-autonomous-agents-data-leakage-mahesh-goyalhttps://offensive.infosecrelations.com/p/live-sessions-2-securing-autonomous-agents-data-leakage-mahesh-goyalFri, 22 May 2026 22:05:21 GMTThe shift from passive LLMs to autonomous, agentic AI introduces a fundamentally new class of security risks. Unlike traditional stateless applications, AI agents are non-deterministic—they hold memory, interact dynamically with multiple APIs, and blur the lines between data and instructions. Existing enterprise security frameworks, built around static roles and predictable user behaviors, are completely blind to the dynamic reasoning and complex attack paths these systems create.

In this session of Offensive Engineering Live Sessions, Mahesh Kumar Goyal, a Senior Data and AI Engineer at Google specializing in advanced agentic AI systems and responsible AI architectures, walks through the mechanics of governing and securing autonomous workflows. He’s speaking independently, and the views he shares are his own.

The conversation covers:

  • Why the non-deterministic nature of agents breaks traditional identity and access management (IAM) frameworks

  • How the line between data and code blurs when documents and log files become instructions for an AI

  • Why prompt injection is evolving into the SQL injection of the agentic era, capable of poisoning long-term memory

  • The critical need to treat an agent’s memory like a database with isolated, ephemeral context windows

  • Why relying on standard enterprise observability and EDR tools for agentic workflows is a dangerous enterprise misconception

  • Mandatory governance controls for production, from centralized agent inventories to unique cryptographic identities and short-lived tokens

]]><![CDATA[Live Sessions #1 Attacking the Control Plane with Siri Verma Veggiraju]]>https://offensive.infosecrelations.com/p/live-sessions-1-attacking-the-control-plane-siri-vermahttps://offensive.infosecrelations.com/p/live-sessions-1-attacking-the-control-plane-siri-vermaWed, 13 May 2026 22:57:59 GMTCloud infrastructure has become the central battlefield for enterprise security, and the control plane is its most consequential layer. Attackers rarely go straight for it. They work through secondary accounts, leaked credentials, and overprivileged identities to reach it — and once they’re there, they can map, enumerate, and exfiltrate at scale. The rise of agentic AI and model context protocols is reshaping that attack surface in ways that most security teams have not yet fully reckoned with.

In this session of Offensive Engineering Live Sessions, Siri Verma Veggiraju, a tech lead at Microsoft Azure Security with hands-on experience across cloud security architecture, identity, and the control plane, walks through the mechanics of how these attacks actually unfold. He’s speaking independently, and the views he shares are his own.

The conversation covers:

  • How the attack landscape against cloud infrastructure has shifted with large language models and agentic AI

  • Why secondary accounts are the real entry point to control plane compromise

  • What a realistic attack chain looked like in the early days of cloud, and why the same principles still apply

  • How managed identities work and where organizations consistently over-privilege them

  • Why API proliferation is a blind spot that most security teams underestimate

  • What least privilege looks like when you’re securing sub-agents in a hierarchical AI architecture

  • How to think about the line between a security incident and a sovereignty problem

]]>