Reducing Attack Surface & Evaluating Efficiency in Agents - Itamar Apelblat, David Goldschlag - ASW #389
Application Security Weekly (Audio)Show Notes
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
More from Application Security Weekly (Audio)
The OWAS Mobile Application Security (MAS) project recently released an updated version of its guidance, with excellent advice organized into common weaknesses, a verification standard for devs (MASVS), and a testing guide (MASTG). Ryan Lloyd and Jan Seredynski from Guardsquare dive into the project to talk about how it's been updated, how orgs can use it, and the challenges orgs face in managing their mobile frameworks and environments. We also cover how agents and LLMs are impacting mobile security and what future iterations of the MAS project might include for securing mobile apps interacting with LLMs or being written by LLMs. Finally, we share practical ways for developers to get involved as OWASP contributors and advocates. Segment Resources: https://mas.owasp.org https://mas.owasp.org/MASWE/ https://hubs.ly/Q04ykvgm0 This segment is sponsored by Guardsquare. Visit https://securityweekly.com/guardsquare to learn more! Visit https://www.securityweekly.com/asw for all the latest episodes! Show Notes: https://securityweekly.com/asw-405
To celebrate our 404th episode we discuss what's not found in modern appsec and what still exists that should become not found. The conversation starts with a classic problem of appsec -- looking for a reliable vuln prioritization methodology. But we expand from there to challenge whether a focus on vulns and patches is even the right choice for an appsec program. Then it's on to incentives, the role of agents in writing and securing software, and what we should be looking for to bring new appsec practitioners into the industry. Visit https://www.securityweekly.com/asw for all the latest episodes! Show Notes: https://securityweekly.com/asw-404
The principle of least privilege access is ubiquitous in recommendations, but perhaps too uncommon in practice. Alex Olivier explains how the AuthZen Working Group has been approaching new standards, guidelines, and practical deployment patterns to make it easier for orgs to establish more refined and correct access policies. It's a problem that predates LLMs, but also one that agents and MCPs made all the more acute. We talk about what intent means when trying to constrain agents' activities, what role LLMs have in policy decisions, and how LLMs can help create a much-needed inventory of access controls. Segment Resources: https://www.cerbos.dev/blog/dimmer-switch-not-a-kill-switch-rethinking-ai-agent-governance https://www.cerbos.dev/blog/multi-hop-delegation-ai-agents https://openid.net/wg/authzen/ Visit https://www.securityweekly.com/asw for all the latest episodes! Show Notes: https://securityweekly.com/asw-403
Finding flaws with LLMs and agents is changing bug bounty programs. But it's not necessarily changing how orgs fix those flaws. Shlomie Liberow shares his experience across a decade of bounty programs and how they have changed for researchers and orgs. He explains why fixing the bug reported through a bug bounty is more about understanding interconnected systems than fixing a single piece of software. We discuss how orgs can be more effective at securing their environment and what role LLMs might have in evaluating controls. Plus, we look to the future of bug bounty programs and how researchers can still excel through curiosity and expertise on a topic rather than relying on scanners, prompts, and luck. Visit https://www.securityweekly.com/asw for all the latest episodes! Show Notes: https://securityweekly.com/asw-402
Prompt injection demonstrates one of the major challenges in securing LLMs and agents -- how do you ensure an agent ignores attackers and only does what you instructed it to do. The flaw highlights how LLMs mix inputs, context, and outputs without any strict boundaries between them. Julie Brunias joins us to talk through examples of injections, why their consequences can go beyond information leaks, and why trying to mitigate them with other LLMs is insufficient. Segment resources: https://llmgateway.io/open-source https://www.wiz.io/blog/off-guard-breaking-litellm-from-authentication-bypass-to-cloud-compromise Visit https://www.securityweekly.com/asw for all the latest episodes! Show Notes: https://securityweekly.com/asw-401