Uploaded July 2026 | Updated September 2026, 2 weeks ago
Orgs need to be able to use agents, MCPs, and LLMs in ways that don't lead to unexpected actions and undesirable outcomes. The OWASP Agent Security Regression Harness project is an approach for defining customizable scenarios and testing whether those systems fail against known security threats. Mert Saltimaz talks about the background of the project, how orgs can use it as they bring more LLMs into their environment, and how the project intends to grow. Importantly, we also talk about the security controls and designs that orgs can build around the systems and data that models interact with in addition to evaluating the security of the agents and agent harnesses themselves.
Segment Resources:
- github.com/OWASP/Agent-Security-Regression-Harness
- youtu.be/6DWs5EwbFQ0?si=r0IJ_F0SZnkPzzYg -- "What Trading Systems Taught Me About Breaking (And Defending) Infrastructure"
Visit securityweekly.com/asw for all the latest episodes!
Show Notes: securityweekly.com/asw-393
00:00:00 From Trading Algorithms to Cybersecurity Expertise
00:11:21 Testing LLM Agents with OWASP Regression Harness
00:22:52 Securing LLM Agents with Proactive Design Principles
00:31:31 Mert's Three Words for Application Security
00:34:05 LLM Escapes Sandbox, Hacks Hugging Face
00:46:03 Proactive vs. Reactive Machine Speed Security
00:55:55 Enhancing Open Source Security with Immutable Releases
00:58:56 Reflux FSA: A Deep Dive into Kernel Vulnerabilities
01:05:27 Restructuring Bug Bounty Programs for Quality
Orgs need to be able to use agents, MCPs, and LLMs in ways that don't lead to unexpected actions and undesirable outcomes. The OWASP Agent Security Regression Harness project is an approach for defining customizable scenarios and testing whether those systems fail against known security threats. Mert Saltimaz talks about the background of the project, how orgs can use it as they bring more LLMs into their environment, and how the project intends to grow. Importantly, we also talk about the security controls and designs that orgs can build around the systems and data that models interact with in addition to evaluating the security of the agents and agent harnesses themselves.
Segment Resources:
- github.com/OWASP/Agent-Security-Regression-Harness
- youtu.be/6DWs5EwbFQ0?si=r0IJ_F0SZnkPzzYg -- "What Trading Systems Taught Me About Breaking (And Defending) Infrastructure"
Visit securityweekly.com/asw for all the latest episodes!
Show Notes: securityweekly.com/asw-393
00:00:00 From Trading Algorithms to Cybersecurity Expertise
00:11:21 Testing LLM Agents with OWASP Regression Harness
00:22:52 Securing LLM Agents with Proactive Design Principles
00:31:31 Mert's Three Words for Application Security
00:34:05 LLM Escapes Sandbox, Hacks Hugging Face
00:46:03 Proactive vs. Reactive Machine Speed Security
00:55:55 Enhancing Open Source Security with Immutable Releases
00:58:56 Reflux FSA: A Deep Dive into Kernel Vulnerabilities
01:05:27 Restructuring Bug Bounty Programs for Quality
