Hello, I'm Harshad
Based in Austin, Texas. By day I’m a Senior Infrastructure Security Engineer at Indeed, where I architect Zero Trust, SASE, edge-native security, and multi-cloud infrastructure at enterprise scale. By night I build and explore whatever has my curiosity: a jack of all trades, and a master of a few.
I build open-source tools in two areas: deception for detecting AI agents (MCP Threat Trap, KubeTrap) and edge infrastructure security (FlareGuard).
Outside of that, I’m a CISM-certified practitioner, a member of ISACA’s Emerging Trends Working Group and Academic & Workforce Development Advisory Group, and the founding chapter lead of AI Security Engineers Austin.
I speak at security conferences on AI security, deception engineering, and edge infrastructure. You can see what I’m working on in my writing and talks.
- Location
- Austin, Texas
- Full time
- Senior Infrastructure Security Engineer, Indeed Inc.
- Community
- Founding Chapter Lead, AI Security Engineers — Austin
- Contact
- [email protected]
Elsewhere
ISACA Now — "Sizing up the State of Cyber: Industry Leaders Pinpoint Workforce Challenges and Solutions"
ISACA Now panel on the State of Cybersecurity 2026 report, with Harshad among the industry leaders interviewed: "What you can verify about an agent is its behavior, not its intent; its stated reasoning is just another output you’d have to trust."
@ISACA — "Five Strategies for Utilizing CPE for Impactful Professional Development"
@ISACA newsletter (2026, Volume 13) quoting Harshad as a member of ISACA's Emerging Trends Working Group: "When you're representing a community or standing in front of peers with original work, the bar is higher — and that's where the real learning happens."
Distilled Security Podcast — "Catching Cloud Drift & Rogue AI Agents"
Interview ahead of BSidesPGH 2026 on cloud misconfiguration drift and detecting AI agents that discover and invoke internal tools.
Thinkst — "One for all the models out there!"
Thinkst — creators of Canarytokens, the deception technology underlying the modern honeytoken ecosystem — published this official announcement of their new MCP server Canarytoken and credited Harshad by name: "Harshad Sadashiv Kadam used our Kubernetes, DNS and Web Bug tokens to create an AI honeypot that would alert only after a client started using the results from tool calls (check it out!)."
Lenny Zeltser — "Build a Decoy MCP Server to Catch AI Agent Attackers"
Independent citation by Lenny Zeltser — SANS Institute Faculty Fellow and creator of REMnux — who cited Harshad's Deception Remote MCP Server by name: "Harshad Sadashiv Kadam's Deception Remote MCP Server takes that approach for a public-facing honeypot any MCP client can discover and connect to."
TechTarget — "Tape's strategic role in modern data protection"
Feature by Mary K. Pratt, quoting Harshad as a member of ISACA's Emerging Trends Working Group: "Low-cost disk and public cloud shifted enterprise backup architectures away from tape. Organizations looked at cloud services not just for day-to-day computing and data processing, but also for backup storage."
Cloudflare Workers Tech Talks — FlareGuard: Automating Security Posture at the Edge
Independent writeup by Nick Gray from Austin's first Cloudflare Workers Tech Talks, where Harshad presented FlareGuard alongside Cloudflare's own engineers — including Kenton Varda (founder of Cloudflare Workers). Nick documented three key insights from the talk: the invisible risk of edge misconfigurations (exposed .env vars, outdated TLS), FlareGuard's Gold Standard YAML baseline approach to auditing every Worker, and the Shadow IT Fix — automatically detecting zombie workers that become attack entry points.