Oktane Preview with Harish Peri, Invisible Prompt Attacks, and the weekly news! - Harish Peri - ESW #421
Enterprise Security Weekly (Audio)
Release Date: 08/25/2025
Holiday Chat: Local AI datacenter activism, AI can't substitute good taste, and more - ESW #439
Enterprise Security Weekly (Audio)
For this week's episode of Enterprise Security Weekly, there wasn't a lot of time to prepare. I had to do 5 podcasts in about 8 days leading up to the holiday break, so I decided to just roll with a general chat and see how it went. Also, apologies, for any audio quality issues, as the meal I promised to make for dinner this day required a lot of prep, so I was in the kitchen for the whole episode! For reference, I made the recipe for from Rick Martinez's cookbook, Mi Cocina. I used the wrong peppers (availability issue), so it came out green instead of red, but was VERY delicious. As for the...
info_outline
Internal threats are the hole in Cybersecurity’s donut - Frank Vukovits - ESW #438
Enterprise Security Weekly (Audio)
Interview with Frank Vukovits: Focusing inward: there lie threats also External threats get discussed more than internal threats. There’s a bit of a streetlight effect here: external threats are more visible, easier to track, and sharing external threat intelligence doesn’t infringe on any individual organization’s privacy. That’s why we hear the industry discuss external threats more, though internally-triggered incidents far outnumber external ones. Internal threats, on the other hand, can get personal. Accidental leaks are embarassing. Malicious insiders are a sensitive topic that...
info_outline
Illuminating Data Blind Spots, Topic, Enterprise News - Tony Kelly - ESW #437
Enterprise Security Weekly (Audio)
Interview Segment: Tony Kelly Illuminating Data Blind Spots As data sprawls across clouds and collaboration tools, shadow data and fragmented controls have become some of the biggest blind spots in enterprise security. In this segment, we’ll unpack how Data Security Posture Management (DSPM) helps organizations regain visibility and control over their most sensitive assets. Our guest will break down how DSPM differs from adjacent technologies like DLP, CSPM, and DSP, and how it integrates into broader Zero Trust and cloud security strategies. We’ll also explore how compliance and...
info_outline
Fix your dumb misconfigurations, AI isn't people, and the weekly news - Wendy Nather, Danny Jenkins - ESW #436
Enterprise Security Weekly (Audio)
Interview with Danny Jenkins: How badly configured are your endpoints? Misconfigurations are one of the most overlooked areas in terms of security program quick wins. Everyone freaks out about vulnerabilities, patching, and exploits. Meanwhile, security tools are misconfigured. Thousands of unused software packages increase remediation effort and attack surface. The most basic misconfigurations lead to breaches. Threatlocker spotted this opportunity and have extended their agent-based product to increase attention on these common issues. This segment is sponsored by ThreatLocker. Visit to...
info_outline
From Misconfigurations to Mission Control: Lessons from InfoSec World 2025 - Marene Allison, Dr. Ron Ross, Ryan Heritage, Patricia Titus, Perry Schumacher, Rob Allen - ESW #435
Enterprise Security Weekly (Audio)
Live from InfoSec World 2025, this episode of Enterprise Security Weekly features six in-depth conversations with leading voices in cybersecurity, exploring the tools, strategies, and leadership approaches driving the future of enterprise defense. From configuration management and AI-generated threats to emerging frameworks and national standards, this special edition captures the most influential conversations from this year’s conference. In this episode: -You Don’t Need a Hacker When You Have Misconfigurations — Rob Allen, Chief Product Officer at ThreatLocker®, discusses how...
info_outline
Aligning teams for effective remediation, Anthropic's latest report, and the news - Ravid Circus - ESW #434
Enterprise Security Weekly (Audio)
Interview with Ravid Circus Ravid will discuss why security and engineering misalignment is the biggest barrier to fast, effective remediation, using data from Seemplicity’s 2025 Remediation Operations Report. This is costing some teams days of unnecessary exposure, which can lead to major security implications for organizations. Segment Resources: Topic Segment: Thoughts on Anthropic's latest security report Ex-SC Media journalist Derek Johnson did a great job writing this one up over at Cyberscoop: There are a number of interesting questions that have been raised here. Some...
info_outline
Year of the (Clandestine) Linux Desktop, topic, and the news - Rob Allen - ESW #433
Enterprise Security Weekly (Audio)
Segment 1: Interview with Rob Allen It’s the Year of the (Clandestine) Linux Desktop! As if EDR evasions weren’t enough, attackers are now employing yet another method to hide their presence on enterprise systems: deploying tiny Linux VMs. Attackers are using Hyper-V and/or WSL to deploy tiny (120MB disk space and 256MB memory) Linux VMs to host a custom reverse shell and reverse proxy. In this segment, we’ll discuss strategies and mitigations to battle this novel technique with Rob Allen from Threatlocker. Segment Resources: This segment is sponsored by ThreatLocker. Visit to...
info_outline
OT Security Doesn't Have to be a Struggle, Spotting Red Flags, Enterprise News - Joshua Hay, Todd Peterson - ESW #432
Enterprise Security Weekly (Audio)
Segment 1: OT Security Doesn’t Have to be a Struggle OT/ICS/SCADA systems are often off limits to cybersecurity folks, and exempt from many controls. Attackers don’t care how fragile these systems are, however. For attackers aiming to disrupt operations, fragile but critical systems fit criminals’ plans nicely. In this interview, we discuss the challenge of securing OT systems with Todd Peterson and Joshua Hay from Junto Security. This segment is sponsored by Junto Security. Visit to learn more! Segment 2: Topic - Spotting Red Flags in Online Posts This week's topic segment is all about...
info_outline
Transforming Frontline Workflows with Passwordless Access, AI costs, and the News - Joel Burleson-Davis - ESW #431
Enterprise Security Weekly (Audio)
Segment 1: Interview with Joel Burleson-Davis Frontline workers can’t afford to be slowed down by manual, repetitive logins, especially in mission-critical industries where both security and productivity are crucial. This segment will explore how inefficient login methods erode productivity, while workarounds like shared credentials increase risk, highlighting why passwordless authentication is emerging as a game-changer for frontline access to shared devices. Joel Burleson-Davis, Chief Technology Officer of Imprivata, will share how organizations can adopt frictionless and secure access...
info_outline
Securing AI Agents with Dave Lewis, Enterprise News, and interviews from Oktane 2025 - Mike Poole, Conor Mulherin, Dave Lewis - ESW #430
Enterprise Security Weekly (Audio)
Segment 1: Interview with Dave Lewis from 1Password In this week's sponsored interview, we dive into the evolving security landscape around AI agents, where we stand with AI agent adoption. We also touch on topics such as securing credentials in browser workflows and why identity is foundational to AI agent security. This segment is sponsored by 1Password. Visit to learn more! Segment 2: Enterprise News In this week's enterprise security news, one big acquisition, two small fundings not all AI is bad deepfakes are getting crazy good make sure you log what your AI agents do Copilot prompt...
info_outlineInterview with Harish Peri from Okta
Oktane Preview: building frameworks to secure our Agentic AI future
Like it or not, Agentic AI and protocols like MCP and A2A are getting pushed as the glue to take business process automation to the next level. Giving agents the power and access they need to accomplish these lofty goals is going to be challenging, from a security perspective.
How do put AI agents in the position to perform broad tasks autonomously without granting them all the privileges? How do we avoid making AI agents a gold mine for attackers - the first place they stop once they hack into our companies? These are some examples of the questions Okta aims to answer at this year’s Oktane event, and we aim to kick off the conversations a little early - with this interview!
Segment Resources:
- Check out securityweekly.com/oktane for all our live coverage during the event this year!
- More information about the event and how you can attend can be found here: https://www.okta.com/oktane/
- AI at Work 2025: Securing the AI-powered workforce
Topic - Indirect Prompt Injection Getting Out of Hand
Reports of indirect prompt injection issues have been around for a while. Of particular note was Michael Bargury's Living off Microsoft Copilot presentation from Black Hat USA 2024. Simply sending an email to a Copilot user could make bad stuff happen.
Now, at Black Hat 2025, we've got more: the ability to plunder any data resource connected to ChatGPT (they call these integrations "Connectors") from Tamir Ishay Sharbat at Zenity Labs. The research is titled AgentFlayer: ChatGPT Connectors 0click Attack.
Looks like Google Jules is also vulnerable to what the Embrace the Red blog is calling invisible prompts. Sourcegraph's Amp Code is also vulnerable to the same attack, which encodes instructions to make them invisible.
What's really going to ruffle feathers is the fact that all these companies know this stuff is possible, but don't seem to be able to figure out how to prevent it. Ideally, we'd want to be able to distinguish between intended instruction and instructions injected via attachments or some other means outside of the prompt box. I guess that's easier said than done?
News
Finally, in the enterprise security news,
- Drones are coming for you… to help?
- One of the most powerful botnets ever goes down
- Phishing training is still pointless
- Microsoft sets an alarm on its phone for 8 years from now to do post-quantum stuff
- vulns galore in commercial ZTNA apps
- GenAI projects are struggling to make it to production
- Adblockers could be made illegal - in Germany
- Windows is getting native Agentic support
- Automating bug discovery AND remediation?
- Public service announcement: time is running out for Windows 10
All that and more, on this episode of Enterprise Security Weekly.
Visit https://www.securityweekly.com/esw for all the latest episodes!
Show Notes: https://securityweekly.com/esw-421