How to Secure Your OpenClaw Agent | Interview with ZioSec Founders

2026-02-04 · 46 min · episode 1 · 8 entities

episode page audio

Asserted relationships

→ appeared on This Week in AI podcast

0.76

evidence rules-v5
How to Secure Your OpenClaw Agent | Interview with ZioSec Founders
→ hosted by Jason Calacanis person

0.55

evidence rules-v5
Feed author/publisher: Jason Calacanis
→ discusses Technology company

0.40

evidence rules-v5
Feed category: Technology
→ references ziosec.com website

0.38

evidence rules-v5
Link in episode "How to Secure Your OpenClaw Agent | Interview with ZioSec Founders": https://ziosec.com/

Entities found in this episode

persons 3

mentioned ZioSec Founders person

0.80

evidence rules-v5
How to Secure Your OpenClaw Agent | Interview with ZioSec Founders
mentioned Jason Calacanis person

0.70

evidence rules-v5
Feed author/publisher: Jason Calacanis
hosted by Jason Calacanis person

0.55

evidence rules-v5
Feed author/publisher: Jason Calacanis

companys 2

mentioned Technology company

0.50

evidence rules-v5
Feed category: Technology
discusses Technology company

0.40

evidence rules-v5
Feed category: Technology

websites 2

mentioned ziosec.com website

0.45

evidence rules-v5
Link in episode "How to Secure Your OpenClaw Agent | Interview with ZioSec Founders": https://ziosec.com/
references ziosec.com website

0.38

evidence rules-v5
Link in episode "How to Secure Your OpenClaw Agent | Interview with ZioSec Founders": https://ziosec.com/

podcasts 1

appeared on This Week in AI podcast

0.76

evidence rules-v5
How to Secure Your OpenClaw Agent | Interview with ZioSec Founders

Episode description as stored

Welcome to the very first episode of This Week in AI! Host Oliver Korzen kicks things off with an exclusive interview featuring Aaron Walls (CEO) and Andrius Useckas (CTO), the founders of ZioSec. Together, they dive deep into the world of OpenClaw security—exposing the vulnerabilities they've discovered in the wild, breaking down real attack vectors, and revealing the essential steps you need to take to protect your agent from exploitation.🔒 Key Takeaways:1. Why Mac Mini might be your safest local setup2. The "Lethal Trifecta" that makes AI agents vulnerable3. How indirect prompt injections hijack your agent through email & documents4. Why 26% of OpenClaw skills contain vulnerabilities5. Input sanitation & judge models as defensive layersZioSec: AI agent assisting in penetration testing | https://ziosec.com Timestamps: 00:00 - Why Mac Mini isn't the right setup for everyone 12:30 - The right way to host OpenClaw (hint: not AWS) 16:11 - Understanding your attack surface 27:33 - Why third-party skills are a security risk 36:30 - Start with sandboxes & read-only permissions 40:03 - Career advice for college students