In this episode of Absolute AppSec, hosts Ken Johnson and Seth Law interview Mohan Kumar and Naveen K Mahavisnu, the practitioner-founders of Aira Security, to explore the critical challenges of securing autonomous AI agents in 2026. The conversation centers on the industry's shift toward "agentic workflows," where AI is delegated complex tasks that require monitoring not just for access control, but for the underlying "intent" of the agent's actions. The founders explain that agents can experience "reasoning drift," taking dangerous or unintended shortcuts to complete missions, which necessitates advanced guardrails like "trajectory analysis" and human-in-the-loop interventions to ensure safety and data integrity. A significant portion of the episode is dedicated to the security of the Model Context Protocol (MCP), highlighting how these integration servers can be vulnerable to "shadowing attacks" and indirect prompt injections—exemplified by a real-world case where private code was exfiltrated via a public GitHub pull request. To address these gaps, the guests introduce their open-source tool, MCP Checkpoint, which allows developers to baseline their agentic configurations and detect malicious changes in third-party tooling. Throughout the discussion, the group emphasizes that as AI moves into production, security must evolve into a proactive enablement layer that understands the probabilistic and unpredictable nature of LLM reasoning.

In this episode of Absolute AppSec, Nathan Hunstad, Director of Security at Vanta, discusses the intersection of security policy, governance, and technical defense. Drawing on his unique background in political science and the Minnesota state legislature, Hunstad argues that policy acts as the essential "conductor" for an organization's security tools. A major theme of the conversation is the challenge of compliance for startups, with the group advising founders to prioritize business survival and basic security hygiene—like password managers and IAM—before pursuing intensive certifications like SOC 2. The discussion also explores how AI is accelerating both development velocity and the ability to automate tedious security questionnaires. Furthermore, Hunstad contrasts the security posture of modern, cloud-native startups against legacy enterprises, noting that older organizations often struggle with "dark corners" of un-inventoried, vulnerable legacy tech. The episode concludes with a critique of outdated authentication standards, specifically advocating for the removal of mandatory password rotation in favor of NIST-aligned, phishing-resistant MFA.

Ken Johnson (cktricky on social media) and Seth Law are happy to announce a special episode of Absolute AppSec with Avi Douglen (sec_tigger on X), long-time OWASP Global Board of Directors member, founder and CEO of Bounce Security and co-author of the Threat Modeling Manifesto. The conversation ranges from Application Privacy related to Application Security, to participating in meetups and conferences, and finally OWASP as an Avi's experience as a board member.

In episode 307 of Absolute AppSec, hosts Ken and Seth conduct a retrospective on the application security landscape of 2025. They conclude that their previous predictions were largely accurate, particularly regarding the rise of prompt injection, AI-backed attacks, and the industry-wide shift toward per-token billing models. A major theme of the year was the solidification of supply chain security as a critical pillar of AppSec, driven by notable incidents such as Shai Hulud and React for Shell. The hosts also share insights from their four-day training course on utilizing LLMs for secure code review, noting that while AI development is becoming more prevalent, most practitioners are still in the nascent stages of building custom tooling. Much of the discussion focuses on the Model Context Protocol (MCP); while it offers significant value for agentic workflows, the hosts criticize its current lack of robust security controls, specifically highlighting issues with OAuth implementations and short timeouts in existing clients. Finally, they discuss how the industry is moving toward a more nuanced balance between deterministic tools like Semgrep and the probabilistic creativity of LLMs to increase efficiency in security consulting.

Given the spate of recent npm news stories, we've arranged a topical show with software supply-chain security researcher and npm hacker Paul McCarty (find Paul on bsky https://bsky.app/profile/6mile.githax.com) . Paul is currently a researcher with Safety (https://getsafety.com/) and has a background in security including work at John Deere, Boeing, Regence Blue Cross/Blue Shield, NASA Jet Propulsion Lab, the US Army, and the Queensland Government. He's also spent twenty some odd years helping startups with security practices, and is a maintainer of the Open Source Malware project. In addition, Paul has been long time friend of the show, contributing his insights to the Absolute AppSec community slack in addition to frequently writing up his research at the SourceCode RED blog: https://sourcecodered.com/blog.

The latest episode of Absolute AppSec is here, with Ken Johnson and Seth Law checking in during the busy Q4 holiday season to share some fascinating insights on the evolving landscape of security and technology. They kick off by reflecting on their intensive, ever-changing "Harnessing LLMs for Application Security" courses, noting how rapidly the underlying tech evolves. The conversation quickly turns to a compelling debate: How will the rise of generative AI impact career paths for newcomers, especially given that LLMs fundamentally rely on the contributions of existing experts? While pathways may change, they agree that core human activities—like networking, contributing to projects, and maintaining a hacker mindset—will remain crucial. The hosts then dive into a fascinating discussion on the darker side of SEO, introducing the concept of Generative AI Engine Optimization (GEO), where marketers exploit AI search results through tricks like keyword-stuffed files to game rankings. They tie this to historical examples of exploitation, harkening back to Google hacking days. Finally, they cover the recent Shai Hulud 2 supply chain attack, which infected hundreds of NPM packages and utilized even more sophisticated obfuscation and delayed execution tactics than its predecessor.

This episode, the 304th of Absolute AppSec, features hosts Ken Johnson (@cktricky) and Seth Law (@sethlaw) discussing the crush of Q4 expectations, upcoming training opportunities, the recent updates to the OWASP Top Ten, and the impact of AI tools like XBow on application security (AppSec) consulting. The hosts discuss the shift in the OWASP Top Ten from focusing on vulnerabilities to focusing on risks, and the dual role the list now plays for both awareness/training and compliance. Shifting to recent funding of XBow, the overall consensus is that while AI tools dramatically improve process flow, scoping, and the speed of vulnerability identification for consultants, they won't replace the need for human experts for complex, bespoke systems, business logic flaws, or authorization issues. AI is commoditizing lower-level AppSec work.

Prof. Brian Glas (infosecdad on social media) joins Seth Law (sethlaw) and Ken Johnson (cktricky) for a timely episode of Absolute AppSec. Infosec Guru and one of the OWASP Top Ten project leaders Prof. Glas joins us in the aftermath of the Global AppSec conference and the announcement of the new OWASP Top Ten (2025). This episode focuses on the process for compiling the list as well as gleaning any other insights from Prof. Glas.

Episode 302 of Absolute AppSec has hosts Ken Johnson and Seth Law speculating on the upcoming Global AppSec DC conference, predicting the announcement of the OWASP Top Ten 2025 edition, with Brian Glass scheduled to discuss it on the podcast. The conversation shifts to a technical discussion of OpenAI's new browser, Atlas, which is built on Chromium and includes AI capabilities. The hosts noted concern over the discovered prompt instructions for Atlas, which direct the ChatGPT agent to use browser history and available APIs to find data from the user's logged-in sites to answer ambiguous queries or fulfill requests. This functionality raises significant security concerns, as the agent's ability to comb the cache and logged-in sites could be exploited, effectively creating a "honeypot for cross-site scripting" with malicious potential like unauthorized money transfers. The hosts discussed the lack of talk submissions on Mobile Context Protocol (MCP) security at the conference, despite its growing relevance in a world of AI agents and tooling. Finally, they highlighted a new tool called SlopGuard, developed to prevent the risk of AI hallucinating non-existent, potentially malicious packages (which occurs 5-21% of the time) and attempting to install them from registries like NPM.

In this episode, Seth and Ken debate OpenAI's Atlas browser, which embeds AI into web browsing. Ken views it as a major privacy concern, potentially accelerating invasive data collection and surveillance. Seth noted that new browsers historically have critical flaws. They acknowledged that AI is very useful for generic and technical internet searches. They discussed the Co-Fish attack, a phishing vulnerability in Microsoft Copilot Studio that could exfiltrate access tokens via a seemingly valid Microsoft URL. Finally, they noted that big companies like Snyk and Black Duck are moving toward agentic AI capabilities, confirming the industry trend.