Secure Talk Podcast

Justin Beals
  • 4.8 (39)
  • Technology
  • Updated Weekly

Secure Talk reviews the latest threats, tips, and trends on security, innovation, and compliance. Host Justin Beals interviews leading privacy, security and technology executives to discuss best practices related to IT security, data protection and compliance. Based in Seattle, he previously served as the CTO of NextStep and Koru, which won the 2018 Most Impactful Startup award from Wharton People Analytics. He is the creator of the patented Training, Tracking & Placement System and the author of “Aligning curriculum and evidencing learning effectiveness using semantic mapping of learning assets,” published in the International Journal of Emerging Technologies in Learning (iJet). Justin earned a BA from Fort Lewis College.

  1. 4d ago

    AI Agent Hacks Another AI Agent Inside Google — An Agentic Supply Chain Bomb

    An agent anyone could talk to just pulled the levers on one almost nobody could reach — and it happened inside the crown jewels: a live code repository. Google gave its AI agent human-level trust — and paid for it.When Dan Lisichkin, a researcher at Pillar Security, started mapping every Google repository running an embedded coding agent, he wasn't hunting for prompt injection — he was hunting classic CI/CD bugs. The AI angle showed up almost by accident, flagged by his own automation. What he found inside Google's Agent Development Kit repository was a low-privilege issue-triaging bot commenting on GitHub *as a trusted collaborator* — a status that should be reserved for humans the maintainers know. As Dan puts it, describing the moment his manager pushed back on downplaying the find: *"this is an agent triggering another agent... this is like no one talked about this before."* The prompt injection wasn't the hard part — weaponizing it was.Dan walks through Pillar's CFS framework (Context, Format awareness, instruction Salience) and how he literally used Google's own CONTRIBUTING.md file as the blueprint for the injection that would slip past the triage agent undetected. From there, one gated comment — normally reserved for trusted maintainers — was enough to trigger a second, far more privileged agent. This isn't a bug you patch once — it's a new attack surface.Dan's read is blunt: multi-agent systems create "weird machine" behavior — undefined states nobody designed for, not flaws in a specific line of code. He and Justin dig into why bolting more rules onto a non-deterministic system is Sisyphean, why bot identities need database-row-level granularity instead of human-style trust, and why Dan — a former malware researcher — thinks mandatory human-in-the-loop is often the wrong answer at scale. Chapters:  00:00: Cold Open: The Agent That Wasn't Supposed to Talk**- Google's public triage bot and the collaborator-status anomaly- Why "an agent triggering another agent" had never been formally described before 04:12:  Building the Hunt: Automation Over Manual Bug-Hunting**- Dan's CI/CD vulnerability scanner, built on top of Claude Code- How an AI-generated "AI agent injection" tag became the whole story- Reference: [Simon Willison — "The Lethal Trifecta for AI Agents"] 14:30: The Exploit: Contribution Guidelines as an Attack Roadmap**- Google ADK repository, the PR-triaging agent, and the CONTRIBUTING.md file used as a weapon- Pillar Security's CFS framework for indirect prompt injection (Context, Format awareness, Salience) — [Pillar Security Blog: Autonomy of Indirect Prompt Injection]- Why jailbreaking ≠ what Dan is doing — "I'm not trying to break the wall, I'm trying to walk through the door it left open" 28:05: Impact: Two Bugs, Two Verdicts**- GitHub token exfiltration, PR/issue metadata manipulation, and the fake "looks good to merge" trail- The second bug: a GCP service account and code-execution potential — "there was more juice on that one"- Why Google didn't pay a bounty — and why that answer is more interesting than the bug itself 38:50:  Identity, Granularity, and the Human-in-the-Loop Debate**- Why bot identities need GitHub App/Actions scoping, not personal-access-token trust- The case *against* blanket human-in-the-loop — review fatigue, OpenClaw, and "people are going to do this anyway"- SolarWinds, CryptoLocker, and why Dan thinks this is a closed-gap problem, not an open one Resources: Lisichkin, D. (2026, August 3). I'll just call you: Agent-to-agent privilege boundary failures in CI/CD on Google's ADK repository. Pillar Security. https://www.pillar.security/blog/ill-just-call-you-agent-to-agent-privilege-boundary-failures-in-ci-cd-on-googles-adk-repository https://danusminimus.github.io/ #aiagents #security #promptinjection #google #defcon #vulnerability---

    AI Agent Hacks Another AI Agent Inside Google — An Agentic Supply Chain Bomb

  2. Aug 11

    AI Is Eating Our Young: Data Center Revolts, Vanishing Junior Jobs & the EU AI Act

    Communities are blocking $130 billion in AI data centers while the entry-level jobs that used to train the next generation of engineers quietly disappear. Chapters:  00:00:  The Backlash: 800 Groups, 49 States, $130B BlockedGallup: 71% of Americans don't want a data center built near them (Gallup)Data center opposition tracker, Q1 2026 filings (referenced industry opposition data)CMMC as precedent for regulating critical infrastructure (DoW CMMC Phase 2 program) 04:30:  Why AI Is "Eating Our Young" in Education**Fran Berman & co-author's unpublished piece on the fraying mid-career pipelineBetter Tech (MIT Press) — Chapter appendix: AI classroom syllabus and exercises 14:00:  Tech as Critical Infrastructure, Not a ReligionBetter Tech prologue: treating tech like food, water, roads, and the power gridGDPR (EU, 2018) as a case study in regulation done right — and its limitsVermont's data broker law as a case study in weak enforcement 26:00: Design Can't Be Bolted On Later**Self-driving cars and the hidden environmental cost of full autonomyAttack surface risk: denial-of-service on connected, self-driving fleets 34:00: Governing the Hybrid Human-AI Society**EU AI Act — risk-tiered regulation: unacceptable, high-risk, low-risk categoriesU.S. Equal Employment Opportunity Commission guidance on algorithmic hiring 41:00: The Hype Curve and the Data Center Reckoning**Western Massachusetts communities rejecting new AI data centersEfficiency vs. quality of life — Berman's closing argument Communities are saying no to AI's biggest infrastructure bet.In the first quarter of 2026 alone, local opposition blocked or delayed 75 data center projects worth roughly $130 billion — nearly matching all of 2025's total in a single quarter. Dr. Fran Berman, former head of the San Diego Supercomputer Center, argues the fix isn't more hype, it's precedent we already have. She points to CMMC itself: "If we can look at the defense supply chain and say this is critical infrastructure, it has to meet a bar, then we can look at the trillion dollars of compute being built into the middle of American life and say the same thing." AI isn't just displacing jobs.  It's starving the pipeline that builds senior engineers. Berman's sharpest warning is about who trains the next generation of professionals when entry-level coding and writing jobs — the ones junior people used to cut their teeth on — get automated away. She compares it to a surgeon who's never had supervised time in the operating room: "Unless you have that experience and the mentorship of more senior professionals, it's really hard" to develop the judgment senior engineers rely on. Good regulation needs more than a law on the books. Drawing on her book Better Tech (MIT Press), Berman walks through why GDPR worked where Vermont's data broker law didn't — and previews how the EU AI Act's risk-tiered approach (unacceptable, high-risk, low-risk) could become the model for governing hybrid human-AI decision-making, where, as she puts it, "the only accountable entities are humans." ✍️ About the AuthorDr. Fran Berman is an award winning-data scientist, pioneer in public interesttechnology, and community leader and builder. She directs the Public InterestTechnology Initiative at UMass Amherst and is a Faculty Associate at the BerkmanKlein Center for Internet and Society at Harvard. Berman is former head the SanDiego Supercomputer Center and served as Vice President for Research atRensselaer Polytechnic Institute. She currently serves as a Trustee of the AlfredP. Sloan Foundation and is a popular regular panelist on public radio’s WAMCRoundtable with 400,000 monthly listeners in seven states. For more information,see https://www.franberman.com. Link to the book: https://mitpress.mit.edu/978026205488...

    AI Is Eating Our Young: Data Center Revolts, Vanishing Junior Jobs & the EU AI Act

  3. Jul 28

    Okta's Identity Chief: Most CISOs Can't Answer This AI Question

    Which AI agents can access what? Are those permissions even right? And can you stop a compromised agent mid-action? Okta's Dan Cinnamon says most enterprises can't answer any of the three. Dan Cinnamon has built software, run SAP GRC without an implementation partner, and now architects identity for one of the industry's biggest players. In this conversation with Justin Beals, he lays out why "discoverability" — simply knowing what agents exist and what they're touching — is the single biggest blind spot in enterprise AI right now, and why there's no silver bullet coming to fix it. They also dig into passkeys as a rare win-win security standard, the maturing MCP spec, and where the hard line on agent containment should actually sit. **Timestamps:** 0:00 Intro 1:20 From writing code to securing identity 4:45 Passkeys: the security/usability unicorn 8:30 The SAP GRC re-implementation story 14:10 Attribution and the agentic AI identity gap 18:55 How fast MCP has matured—and what's next 23:40 The 3 unanswered questions every enterprise faces 27:15 Granular identity vs. inherited permissions 32:00 Containment: moving controls closer to the data 36:45 Consent, provenance, and healthcare AI 40:30 Closing thoughts #CISO #AIstrategy, #enterprise #AIsecurity, #agentic #AIgovernance, #Okta #MCPstandard,  #zerotrust #AI agents

    Okta's Identity Chief: Most CISOs Can't Answer This AI Question

  4. Jul 17

    Special Episode: CMMC Phase 2 SUSPENDED: What DOD Just Did, What It Really Means, and Why Little Changed

    The Pentagon paused CMMC Phase 2 with zero warning — and half the defense industrial base is celebrating for the wrong reason. When the Department of War suspended CMMC Phase 2 rollout with no notice, panic spread fast across the defense contractor community — but the requirement to secure CUI never went away. In this special roundtable, host Justin Beals brings together three CMMC insiders — Logan Therrien (C3PAO Chief Strategy Officer, retired Navy submariner), Lance Arnold (30-year industry veteran, just completed his own CMMC Level 2 journey), and Brian Hubbard (President, Evolved Cyber Solutions, CMMC assessor since 2015) — to separate what actually changed from what didn't. They break down the difference between the assessment requirement (paused) and the security implementation requirement (still very much alive under NIST 800-171), why "self-assessment" doesn't mean "no requirement," and what small businesses and primes should do right now instead of waiting for clarity that may not come for months. Sources Referenced: DFARS 252.204-7021 (CMMC assessment clause) DFARS 252.204-7012 (NIST 800-171 compliance clause) DFARS 252.204-7019 (SPRS scoring requirement) 32 CFR Part 170 (CMMC Program Rule) 32 CFR Part 48 NIST SP 800-171 / NIST SP 800-172

    Special Episode: CMMC Phase 2 SUSPENDED: What DOD Just Did, What It Really Means, and Why Little Changed

  5. Jul 14

    An AI Security Maturity Model for CISOs, with Chris Cochran (SANS)

    Half the room at Chris Cochran's leadership dinners still calls themselves AI skeptics. He argues they can't afford to be — because the adversary already isn't. Chapters:  00:00 — Intro 02:49 — NSA/threat intel → AI security, storytelling 09:55 — Why leaders feel stuck / no roadmap 14:41 — Three pillars (Protect/Utilize/Govern) 17:00 — Governance as the real foundation / shadow AI 21:37 — Evidence-based scoring vs. pass/fail 26:27 — EU AI Act 28:44 — Fable/Mythos, Project Glasswing access controls 33:18 — Token subsidies, self-hosted models 37:52 — Data poisoning & context poisoning 40:12 — Iron Man suit framing 42:38 — Close: what's next

    An AI Security Maturity Model for CISOs, with Chris Cochran (SANS)

  6. Jun 16

    Considering Security, Compliance and Revenue with David Grazer

    Most companies chase certifications to win deals — but what actually keeps customers is something no audit can measure. In this episode, vCISO David Grazer makes the case that trust is a measurable economic asset hiding in plain sight: your customer retention rate. Drawing on 15+ years inside high-growth tech companies, David explains why compliance frameworks are customer acquisition tools, not retention strategies — and how the gap between the two is costing businesses more than they realize. This episode is for founders, security leaders, and C-suite executives who want to connect their security and privacy programs to real business outcomes. You'll learn: → Why a SOC 2 or ISO 27001 certification is only the beginning of earning customer trust → How customer churn functions as one of the most honest security metrics available → Why MFA and common security controls often fail the users who need them most → What "Trust by Design" looks like in product development and AI programs → How to translate security risk into language that resonates with your CFO Chapters 00:00 Introduction to Secure Talk and Trust 03:42 David Grazer's Journey into Security and Privacy 08:09 Navigating Compliance and Customer Trust 12:49 The Role of Consulting in Security 18:07 Trust as a Measurable Economic Asset 23:42 Identity Management in the Entertainment Industry 26:09 The VC SO Model and Its Impact 29:13 The Evolution of Compliance Conversations 33:17 Exploring the Intersection of Technology and Society 🔔 Subscribe to SecureTalk for weekly conversations at the intersection of cybersecurity, compliance, and business strategy. #cybersecurity #compliance #CISO #trustbydesign #vciso #informationsecurity #GRC #dataprivacy

    Considering Security, Compliance and Revenue with David Grazer

  7. Jun 2

    Why you could fail your CMMC Level 2 C3PAO audit | Secure Talk with Logan Therrien

    You did your self assessment and received a perfect 110 score, congratulations! You met with your C3PAO and scored less than 0. What happened! How can two CMMC assessors examine the same defense contractor and arrive at completely different scores? A lack of rigor in assessment methodology could mean the entire certification system is measuring the assessor — not your security. Logan Therrien, Chief Strategy Officer at Kieri Solutions and one of the original C3PAO lead assessors in the U.S., joins Justin Beals to expose a critical flaw in how CMMC Level 2 assessments are conducted today: no standardized evidence sampling methodology. This episode is for DoD contractors, compliance consultants, and defense industry executives who want to understand what's at stake — and how to navigate assessments before the rules tighten further. What you'll learn: Why NIST 800-171 was intentionally vague — and how that backfired for assessorsHow one assessor might review a single evidence point while another reviews 100%What ISO 17020 accreditation will require of C3PAOs and why it matters nowWhat the 48 CFR expansion means for 118,000+ contractors in the supply chainHow to prepare for an assessment so it feels like an open-book test Logan also co-authored the peer-reviewed paper "The Need for Standardized Evidence Sampling in CMMC Assessments: A Survey-Based Analysis of Assessor Practices" (with John Hastings) — one of the first data-driven studies of assessment methodology in the CMMC ecosystem. Chapters 00:00 Introduction to Secure Talk and Psychometrics 01:45 Understanding CMMC and Its Implications 05:32 Logan Therian's Background and Insights 09:16 The Challenges of Assessment Methodologies 16:10 The Scale and Impact of CMMC Assessments 20:31 Navigating Standards in Cybersecurity 23:53 Evidence Testing in CMMC Assessments 27:43 The Importance of Reliable and Accurate Assessments 36:22 Building Trust Between Industry and Defense 41:46 Future Directions in CMMC Research Resources: Therrien, Logan and Hastings, John. (2026, February 10). The need for standardized evidence sampling in CMMC assessments: A survey-based analysis of assessor practices. arXiv. https://arxiv.org/abs/2602.09905

    Why you could fail your CMMC Level 2 C3PAO audit | Secure Talk with Logan Therrien

  8. May 19

    Mark Zuckerberg has an AI twin. Who Is Mark Zuckerberg?

    Mark Zuckerberg built an AI version of himself that attends meetings and approves budgets while he's elsewhere. That's not science fiction — it's happening now. But when an AI replica makes a consequential decision, who's legally responsible? Who owns it when you die? Dr. Candi Cann, Thanatologist and professor at Baylor University, joins SecureTalk host Justin Beals to explore the uncomfortable intersection of technology, mortality, and identity — and what it means for data governance, digital rights, and the future of enterprise accountability. In this episode: Key topics: digital identity, AI accountability, data governance, CMMC compliance, death technology, digital ethics, AI agents, enterprise security If your organization is deploying AI agents that act on behalf of humans — approving transactions, attending meetings, representing employees — this episode raises the governance questions your security and legal teams need to be asking right now. Subscribe to SecureTalk for weekly conversations at the edge of cybersecurity, compliance, and technology culture. Resources: Book: Augmented: Life and Death as a Cyborg by Candy Cann, MIT Press, 2026. Link: https://mitpress.mit.edu/9780262051118/augmented/

    Mark Zuckerberg has an AI twin. Who Is Mark Zuckerberg?
See All (260)

4.8
out of 5
39 Ratings

About

Secure Talk reviews the latest threats, tips, and trends on security, innovation, and compliance. Host Justin Beals interviews leading privacy, security and technology executives to discuss best practices related to IT security, data protection and compliance. Based in Seattle, he previously served as the CTO of NextStep and Koru, which won the 2018 Most Impactful Startup award from Wharton People Analytics. He is the creator of the patented Training, Tracking & Placement System and the author of “Aligning curriculum and evidencing learning effectiveness using semantic mapping of learning assets,” published in the International Journal of Emerging Technologies in Learning (iJet). Justin earned a BA from Fort Lewis College.

Information

  • Creator
    Justin Beals
  • Years Active
    2018 - 2026
  • Episodes
    260
  • Rating
    Clean
  • Copyright
    © All rights reserved
  • Show Website
    Secure Talk Podcast

You Might Also Like