Inside the OWASP Agent Security Regression Harness Project - Mert Satilmaz - ASW #393
28 July - 1 hour 9 minsOrgs 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 Resour...
Series Episodes
Defending at AI Speed as Quantum Threats and AI Policies Won't Save You - Nolan Karpinski - BSW #467
54 mins
30 September Finished
Venus in Furs, Money Laundering, AI Hijinx, MCP, Thunderbastard, and Aaran Leyland - SWN #620
32 mins
29 September Finished
Going From Bug Bounty Bugs to More Secure Systems - Shlomie Liberow - ASW #402
1 hour 2 mins
29 September Finished
AI butterfly effects, Chuds, CISA, FBI, FreeBSD, Ghost Accounts, Pervs, Josh Marpet - SWN #619
32 mins
25 September Finished
