Secure Talk Podcast

She helps write the rules the entire U.S. defense industrial base gets assessed against — and she's telling you compliance is the floor, not the finish line.

Victoria Yan Pillitteri leads the Risk Management Framework/FISMA team at NIST and co-chairs the Joint Task Force uniting DoD, the Intelligence Community, and civilian agencies on one cybersecurity framework. In this episode, she and Justin Beals go inside how NIST actually builds SP 800-53 and 800-171 — what gets cut, what stays, and why "just copy the control language" is a losing strategy for anyone trying to pass an assessment.

In this episode:
Why 853 is "the Cheesecake Factory menu" of cybersecurity controls — and why that's a feature, not a bug
The real difference between NIST 800-171 Rev 2 and Rev 3, and why "organization-defined parameters" changed everything
Why writing your own control (not just quoting NIST's language) is the only way to actually pass an assessment
How FedRAMP 20x, OSCAL, and continuous monitoring are quietly replacing the point-in-time ATO
NIST's upcoming AI control overlays for predictive, generative, and agentic AI systems

Chapters
00:00 Introduction
00:34 The purpose of NIST standards and measurement science
02:24 Cybersecurity outcomes as a Rosetta Stone
03:14 The challenge of measuring risk in cybersecurity
04:55 Frameworks as operating systems for risk management
06:58 The iterative process of developing cybersecurity standards
08:11 Interpreting control statements for organizations
09:36 The importance of tailoring controls to risk profiles
12:30 The relationship between compliance and good risk management
14:37 The development process of cybersecurity standards
17:27 Differences between Rev2 and Rev3 of NIST 800-171
20:01 Broad versus specific requirements in cybersecurity controls
22:36 Supporting small businesses with guidance and tools
27:23 The balance between prescriptive and flexible standards
30:24 Cybersecurity in public-private partnerships
34:53 Moving from point-in-time to continuous authorization
40:23 AI risks and the development of tailored controls
44:53 The future of cybersecurity standards and AI security

Resources referenced:
NIST SP 800-53 (Security and Privacy Controls) — [link]
NIST SP 800-171 Rev 2 & Rev 3 (Protecting CUI) — [link]
NIST Risk Management Framework — [link]
NIST Cybersecurity Framework — [link]
NIST AI Risk Management Framework — [link]
FedRAMP 20x Program — [link]
OSCAL (Open Security Controls Assessment Language) — [link]

#NIST80053 #NIST800171 #CMMC #FedRAMP #CyberCompliance #RiskManagement #CUI #SecureTalk

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
---

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 Blocked
Gallup: 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 pipeline
Better Tech (MIT Press) — Chapter appendix: AI classroom syllabus and exercises

14:00:  Tech as Critical Infrastructure, Not a Religion
Better Tech prologue: treating tech like food, water, roads, and the power grid
GDPR (EU, 2018) as a case study in regulation done right — and its limits
Vermont'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 autonomy
Attack 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 categories
U.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 centers
Efficiency 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 Author
Dr. Fran Berman is an award winning-data scientist, pioneer in public interest
technology, and community leader and builder. She directs the Public Interest
Technology Initiative at UMass Amherst and is a Faculty Associate at the Berkman
Klein Center for Internet and Society at Harvard. Berman is former head the San
Diego Supercomputer Center and served as Vice President for Research at
Rensselaer Polytechnic Institute. She currently serves as a Trustee of the Alfred
P. Sloan Foundation and is a popular regular panelist on public radio’s WAMC
Roundtable 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...

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

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

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

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

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 assessors
• How one assessor might review a single evidence point while another reviews 100%
• What ISO 17020 accreditation will require of C3PAOs and why it matters now
• What the 48 CFR expansion means for 118,000+ contractors in the supply chain
• How 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

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/

The biggest cybersecurity failures in recent memory — Raytheon, Penn State, Georgia Tech — weren't caused by missing software. They were caused by the wrong people being assigned the wrong tasks, with no shared language to connect the rules to the work.

This SecureTalk episode with Dorian Cougias (MoxyWolf, former Unified Compliance Framework CEO) is one of the most systems-level conversations we've had on the show. Dorian spent decades building the infrastructure that compliance programs run on — and he's now rebuilding it from scratch, in the open.

What you'll hear:

→ Why the compliance industry is structurally fragmented across three authority domains that don't communicate

→ How Bloom's Taxonomy — a tool from education — maps directly to which compliance tasks belong to which roles

→ Why the Oxford English Dictionary doesn't have "personal data" in it, and what that tells us about regulatory language

→ The O*NET framework and why the Department of Labor might be the most underused tool in cybersecurity

→ Shannon's entropy theory, applied to compliance and cognitive load

→ A new open-source STIG API infrastructure that StrikeGraph is integrating as a launch partner

Whether you're deep in the compliance trenches or just fascinated by how complex systems fail — and how to redesign them — this is worth your time.

🔗 strikegraph.com | stigviewer.com

Chapters:

00:00 Introduction and Background

02:43 Exploring Compliance and Natural Language Processing

05:15 Military Experience and Signal Intelligence

08:01 Cognitive Load and Compliance Frameworks

10:49 The Importance of Language in Compliance

13:39 The Evolution of Dictionaries and Lexicons

16:16 Bridging Gaps in Compliance Communication

18:47 Innovations at MoxieWolf and Future Directions

22:04 Mapping Skills and Regulatory Guidelines

25:05 Job Applicability and Knowledge Requirements

28:02 The Importance of O*NET in Cybersecurity

29:21 Challenges in CMMC Compliance

33:23 The Role of Technology in Compliance

35:38 Horizontal Practices in Compliance

38:15 Building Effective Teams for Compliance

42:21 Introduction to Compliance Failures

45:19 The Human Element in Compliance

48:10 Navigating Compliance Complexity with Technology

48:57 Introduction to Cybersecurity Compliance Challenges

54:09 The Role of People in Compliance Success

56:01 Guest Introduction: Dorian Cougas

01:00:48 Exploring Bloom's Taxonomy in Compliance

01:05:48 The Importance of Shared Lexicons

01:09:32 Navigating Compliance with Technology

01:15:11 MoxieWolf's Approach to Compliance

01:20:49 The Interconnectedness of Compliance Tasks

01:27:51 Real-World Compliance Challenges

01:33:57 Building Effective Teams for Compliance

#Cybersecurity #ComplianceCulture #CMMC #HumanFactors #GRC #TechPolicy #SecureTalk