Application Security Weekly (Audio)

While LLMs and agents are new to appsec and everyone else, a lot of AI security requirements translate to well-known API security requirements. Jeremy Snyder helps us frame the OWASP LLM Top 10 into five layers in order to help orgs understand and prioritize their attack surface. A lot of orgs don't have to deal with model-specific threats or building their own GPU architecture, but every org adopting LLMs and agents should be aware of how those agents are being invoked and the output those agents are producing. That awareness of input and output helps in identifying and mitigating prompt injection attacks, ensuring agents are working within their expected boundaries, and taming token budgets.
Resources:
https://genai.owasp.org/llm-top-10/
https://github.com/rtk-ai/rtk
https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-caching.html
https://www.firetail.ai/blog/beyond-the-spectacle-rsac-2026-and-the-5-layers-of-ai-security
Visit https://www.securityweekly.com/asw for all the latest episodes!
Show Notes: https://securityweekly.com/asw-391

Mobile applications have unique risks and threat models compared to server-side applications and infrastructure. Consequently, they need different strategies to ensure their business logic and workflows well secured. We'll dive into some of these defense-in-depth strategies and why they are important to mobile applications. Securing workflows goes beyond input validation and pattern matching suspicious payloads; it requires detailed attention to state machines, edge cases, and collecting signals to evaluate trust.
Segment Resources:
https://hubs.la/Q04jLKj70
https://mas.owasp.org/MASTG/0x04c-Tampering-and-Reverse-Engineering/
https://owasp.org/API-Security/editions/2023/en/0x00-header/
This segment is sponsored by Guardsquare. Visit https://securityweekly.com/guardsquare to learn more about them!
Visit https://www.securityweekly.com/asw for all the latest episodes!
Show Notes: https://securityweekly.com/asw-390

SquidBleed reveals another vuln that's been lurking for decades, but its real lesson is in managing an attack surface. Regardless of whatever programming language you use, removing code is one of the best security steps you can take, followed by changing default configs to turn off uncommon features and ancient protocols.
The Linux kernel's removal of strncpy is another example of managing attack surface by replacing a notoriously misused and ambiguous function with more specific versions that better match the developers intent. It was a six-year journey for the kernel, but one that should remove a class of vulns and, importantly, improve performance.
Then it's on to agents with a discussion of the newly released OWASP AISVS and yet another example of evaluating LLMs as code reviewers.
Agentic AI Has an Identity Problem
AI agents are already running inside enterprise environments, operating on credentials, API tokens, and cloud roles that most security teams have never inventoried. When an agent acts autonomously across production systems, the security question is no longer just what it can do but who it is and whether that identity is governed at all. Itamar Apelblat, Co-Founder and CEO of Token Security, discusses why identity is the right lens for understanding agentic AI risk and what practical steps security teams can take now.
Segment Resources:
https://www.token.security/product
https://www.token.security/lp/ai-agent-identity-security-buyers-guide-ebook
https://www.token.security/enzo
https://www.token.security/ai-agent-calculator
This segment is sponsored by Token Security. To lean more, visit https://securityweekly.com/tokenidv
Blended Identities and the challenge of IAM for AI
AI agents aren't quite human and aren't traditional machines. So how do you secure workflows that involve humans using AI to access sensitive data, and do it at machine speed and scale? David breaks down the challenges and discusses actual implementations of IAM for AI to explain how to solve them.
Segment Resources:
https://aembit.io/case-study/a-300b-investment-firm-secures-claude-access-with-aembit/
https://aembit.io/blog/aembit-now-secures-microsoft-copilot-studio-agents/
https://www.youtube.com/watch?v=cSInzRUXvNc
This segment is sponsored by Aembit. Get the cloud security alliance survey on AI Identities at https://securityweekly.com/aembitidv
Visit https://www.securityweekly.com/asw for all the latest episodes!
Show Notes: https://securityweekly.com/asw-389

Appsec has seen machine identities from daemons and processes to services, microservices, and cloud accounts. And now we have agents. Ev Kontsevoy talks about what it means to have engineers and agents interacting in an environment, and why a focus on actions can be more effective than roles. One of the biggest challenges in securing agents along with all of the other identities that organizations manage is how fragmented that management has become. But a unified engineering view of identities is just a start. Once you're able to shift to a practice where access is granted based on attributes and limited durations, then your environment becomes more resilient to mistakes and unexpected actions, not to mention the security concerns that come with agents acting on their own.
Who Is Responsible for an AI Agent's Actions? As AI agents gain the ability to access systems, invoke tools, and take action on behalf of users, organizations need clear frameworks that define responsibility for machine-driven decisions and outcomes. This segment examines how accountability, delegation, and attribution can be established across users, developers, security teams, and business stakeholders. Neha will explore how governance models support transparent, auditable agent-driven workflows while helping organizations manage risk and maintain trust.
This segment is sponsored by P0 Security. Visit https://securityweekly.com/p0idv to learn more about them!
The rapid rise of agentic AI and non-human identities is fundamentally reshaping the future of identity security, challenging traditional IAM and PAM models built around predictable human behavior. In this executive interview at Identiverse 2026, Amit Masand discusses how autonomous systems, AI agents, and machine identities are creating new operational and governance challenges for modern enterprises. Drawing from more than two decades of industry experience, the conversation explores the growing complexity of continuous governance in a world where identities increasingly operate at machine speed.
Segment Resources: https://www.idmexpress.com/post/preventing-cybersecurity-incidents-through-managed-services https://www.idmexpress.com/post/cyberark-securing-aws https://www.idmexpress.com/post/turning-roadblocks-into-breakthroughs-a-custom-oracle-pam-integration-story
Contact IDMEXPRESS! Secure Your Tomorrow, Today: https://securityweekly.com/idmidv
Visit https://www.securityweekly.com/asw for all the latest episodes!
Show Notes: https://securityweekly.com/asw-388

Agents and LLMs are creating and reviewing code. They're a new tool to help developers write software and they're a new abstraction layer for expressing what code should do. But if we're focused on determining whether code is secure, where do we focus our attention on ensuring a secure outcome? Matias Madou talks about the challenges of finding metrics to help answer these questions. We walk through many of the questions we'd like to see answered and our desire to see appsec (finally?) shift out of a find-and-fix mode into a future of secure design.
Visit https://www.securityweekly.com/asw for all the latest episodes!
Show Notes: https://securityweekly.com/asw-387