Bryce Kunz and Shelby Pettit discuss AgentShield, research into behavioral signals that distinguish the tested browser agents from human visitors. They unpack form interactions, typing patterns, hidden page instructions and how an agent's surrounding tools change what it sees and follows. Bryce also shares his account of an unexpected roughly $400 checkout through a logged-in browser, prompting a conversation about isolated sessions, approval gates and hard spending limits.

Shelby then covers malicious Claude Code-branded extensions distributed through Cursor's marketplace: a familiar name and a functioning extension are not enough to establish trust. The conversation explores attempted SSH access, persistence, marketplace security and the practical work of investigating an affected machine.

Finally, a trip through fingerprint.garden leads to a researcher's report of anti-LLM obfuscation: misleading names and alarming text that caused some tested AI tools to refuse analysis of a browser-fingerprinting script. Plus: Halloween candy, movie anticipation and a few very unserious tax jokes.

SOURCE CONTEXT
AgentShield's published form measurements concern reaction to newly revealed fields, not total form-completion time. Its stalled-checkout setup specifies 120 seconds; the conversation paraphrases some timings differently. The findings concern the evaluated clients and a small human baseline, not a guarantee of detecting every agent.

Cursor's notice covers malicious versions 2.1.312 and 2.1.313 for Windows and macOS from its marketplace on October 29, 2026. These malicious versions were not developed by Anthropic. The SSH connection and HTTP beacon use different ports: 22 and 8099, respectively. The cleanup scripts are linked from Cursor's notice, and removing the extension alone may not remove persistence.

Find the show: https://aicyber.land

CHAPTERS
0:00 Welcome & the almost joke-free introduction
0:50 AgentShield: can websites spot an AI agent?
3:16 Bryce's unexpected $400 checkout
4:55 Why familiar browser signatures are not enough
5:24 Form timing, typing & behavioral signals
7:21 What happens when agents try to act human?
7:52 Hidden page instructions & agent harnesses
9:56 Stalled checkouts & policy drift
11:22 Shopping risks & spending limits
12:57 The trojanized Claude Code extension in Cursor
14:51 Signing questions & the software supply chain
16:26 Investigating affected systems & cleanup guidance
18:34 Halloween candy & movie anticipation
19:36 Exploring fingerprint.garden
21:17 Anti-LLM obfuscation & reverse engineering
23:11 Jokes, guardrails & final thoughts
24:27 Goodbye

RESOURCES
AgentShield research: https://arxiv.org/html/2610.41181v1
Cursor security notice and cleanup guidance: https://cursor.com/en-US/blog/claude-code-extension-security-notice
Anti-LLM obfuscation report: https://nullpt.rs/fingerprinting-bioweapons

Topics: #AI #Cybersecurity #AIAgents

Shelby Pettit and Bryce Kunz discuss research on malicious LLM API routers, including payload injection and credential theft. They compare paid and free intermediaries and explain why a proxy with access to prompts and tool responses belongs inside your security threat model—not outside it.

Next, Bryce uses a babysitter analogy to explain a reported attack involving AGENTS.md and CLAUDE.md instruction files. A malicious file in a Downloads folder can influence an agent that operates in and trusts that directory. The hosts discuss browser download prompts, reviewing instruction files and restricting filesystem access. These are defense-in-depth measures, not a guarantee that a browser toggle alone stops every prompt-injection attack.

The conversation also covers NVIDIA OpenShell and the company's recently announced hardware-backed agent-security architecture. This is a discussion of announced controls, not an independently tested guarantee. The episode closes with flowers, kindness, Halloween plans and a turn-based Final Fantasy recommendation.

Find the show: https://aicyber.land

CHAPTERS
0:00 Welcome, hype man Bryce & Halloween
1:14 Why LLM API routers are a trust boundary
2:52 Payload injection & secret exfiltration
3:53 Paid versus free routers: what the study found
5:01 Router samples, canary credentials & poisoning
6:32 LiteLLM & the API-key gray market
7:34 Malicious responses reaching the client
8:43 The babysitter-instructions analogy
9:23 Downloads folders & poisoned agent instructions
11:07 Browser prompts & reviewing instruction files
13:09 NVIDIA OpenShell & hardware-backed controls
15:08 Flowers & a shout-out to kind people
16:53 Halloween plans & a turn-based Final Fantasy game
18:34 Wrap-up & Happy Halloween

SOURCES & CONTEXT
Router study — Your Agent Is Mine (arXiv preprint):
https://arxiv.org/abs/2604.08407

Forever Security — Markdown Is the New Executable:
https://forever.security/blog/hijacking-ai-agents-via-downloads-folder/

NVIDIA OpenShell Reference Architecture (official announcement, October 21, 2026):
https://nvidianews.nvidia.com/news/openshell-reference-architecture

The router counts describe the researchers' sample, not every provider. Forever Security found a malicious file on a customer machine and separately demonstrated browser delivery; the original file's arrival route was unknown. We discuss the hosts' explanations and opinions, not a guarantee that any one mitigation prevents every attack.

Subscribe for more conversations about AI and cybersecurity, and tell us which agent-security topic you want us to cover next.

Topics: #AI #Cybersecurity #AIAgents #PromptInjection

Bryce Kunz and Shelby Pettit discuss OpenAI's report of a training agent reaching an external chatbot through a DNS-filtering gap, then a separate red-team exercise in which agents were asked to exchange synthetic secrets using CPU-cache timing. They compare the published alert and shutdown timeline with the practical problem of stopping a run when containment fails.

Shelby explains abliteration and ProjectDiscovery's demonstration of a backdoored Qwen2.5-7B-Instruct model. The hosts discuss poisoned adapters, trigger phrases, remotely changeable payloads and the risks of trusting modified weights. The demonstration used dummy credentials and limited test sets; it does not establish that all modified models are compromised or that every backdoor is undetectable.

SOURCE CONTEXT
The two OpenAI accounts describe separate events. The DNS incident involved an agent contacting an external chatbot; the CPU-cache experiment explicitly asked agents to communicate. OpenAI attributes the shutdown delay to a failure of automatic stopping and operational confusion, and says that particular model was not resumed. ProjectDiscovery's proof of concept used poisoned adapter training; abliteration and malicious backdooring are not the same thing.

Plus: The Adventures of Elliot: The Millennium Tales, a Chinese money plant, and a confession about secretly replacing a dead tree.

Which boundary would you check first in an AI-agent deployment: network access, accessible secrets, or tool permissions? Tell us in the comments, and subscribe for more AI and cybersecurity conversations.

RESOURCES
OpenAI DNS incident report: https://alignment.openai.com/misalignment-reports/an-agent-used-dns-to-reach-an-external-chatbot/
OpenAI containment and red-team experiments: https://openai.com/index/securing-our-frontier-model-training-environment/
ProjectDiscovery model-backdoor demonstration: https://projectdiscovery.io/research/how-abliterated-models-can-get-you-pwned
Show: https://aicyber.land

KEY MOMENTS
00:00 Welcome & the subscribe joke
01:23 A locked-room analogy for offline AI agents
02:56 DNS: the gap in a no-internet setup
04:47 Alerts, human response & shutting down a run
06:04 Allowed tasks, blocked DNS & the restart discussion
07:08 A separate red-team communication experiment
08:02 CPU-cache timing as a covert channel
09:37 What were the agents actually asked to do?
11:03 Abliterated models & nunchuck-sword security
11:55 Editing a model's refusal direction
13:06 Trigger-activated backdoors in modified models
14:08 Remote payloads & a trigger phrase
15:38 Dummy credentials, poisoned data & dormant behavior
17:08 Model supply chains & compromised intermediaries
19:05 The Adventures of Elliot & the fun-facts segment
20:25 The happiness-coach detour: be present
21:19 A Chinese money plant & secretly replaced trees
22:54 Wrap-up & goodbye

Topics: #AI #Cybersecurity #AISecurity #ModelSecurity

Shelby Pettit and Bryce Kunz discuss the newly disclosed PHP vulnerabilities, AI-assisted vulnerability discovery, and the challenges of coordinating fixes before disclosure details spread. Shelby shares the patching guidance; Bryce argues that finding bugs is only the beginning: teams also need to fix their code and deploy it quickly, with a practical emergency-testing strategy.

Then they unpack AfterDeleteBench, research into information that can survive deletion in an AI agent's external memory. The conversation explores summaries, logs, reconstructed secrets, and why a reassuring answer is not proof that every copy is gone. The paper's roughly two-thirds recovery result concerns a specific controlled Qwen2.5-7B-Instruct setting—not all AI assistants or consumer chat products. Zero data retention, private chats, and guaranteed deletion are different things.

Plus: Shelby's Japanese-inspired nail art and Ramune theme, Bryce's Disneyland trip, and a candid comparison of boutique appointments on land versus at sea.

What is your team's emergency patching bottleneck: finding the issue, fixing the code, or getting the fix deployed? Let us know in the comments, and subscribe for more AI and cybersecurity conversations.

RESOURCES
PHP version checker / Codex skill: https://github.com/openai/php2shell-checker
PHP Foundation release guidance: https://thephp.foundation/blog/2026/10/21/todays-php-security-release-and-how-were-strengthening-php-security/
OpenAI: Patch the Planet coordination: https://openai.com/index/coordinated-disclosure-of-critical-vulnerabilities/
AfterDeleteBench paper: https://arxiv.org/abs/2610.31366v1
Show: https://aicyber.land

KEY MOMENTS
00:00 Welcome, superintelligence & the subscribe pitch
00:56 PHP2Shell: the vulnerability chain
02:20 Emergency patching & checking PHP versions
04:02 Disclosure leaks & coordinated response
06:43 Preparing for more AI-discovered vulnerabilities
08:05 Find, fix, deploy: where defenders should focus
10:05 Emergency testing & patching trade-offs
12:01 AfterDeleteBench: can AI forget a secret?
13:13 Secrets in summaries, logs & memory
14:42 Zero data retention & private-chat controls
16:03 What would genuine deletion require?
17:10 Don't share unnecessary secrets
18:01 Shelby's nail art & Ramune
18:47 Bryce's Disneyland trip & character dining
20:03 Boutique appointments: Disneyland versus a cruise
21:08 Wrap-up & a final patch reminder

Topics: #AI #Cybersecurity #PHP #AISecurity

▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬

🎙️ IN THIS EPISODE:

Welcome to the AiCyber.Land podcast, your home for all things at the intersection of artificial intelligence and cybersecurity! Join your hosts Bryce and Shelby as they explore the breaches, breakthroughs and mind-bending ideas shaping our digital world.

🎭 Deceive the Malware: Bryce unpacks ORCAGen, a research paper posted to arXiv on October 8th. Inspired by the fighter-pilot OODA loop (Observe, Orient, Decide, Act), the system doesn't just kill malware on sight. It detects what the malware is trying to do from the API calls it makes, then quietly feeds it fake data, like LLM-generated keystrokes in place of your real ones, so defenders can watch what it does next. Trained on synthetic malware and defensive playbooks, it defeated 92% of real keyloggers, 100% of info-stealers and 96% of ransomware samples across 150 real-world samples. Plus a simpler place to start (honey tokens), why security rewards early adopters, and whether AI reverse engineering means the end of closed-source software and the start of the patent wars.

🧪 Vercel's $1M Sandbox Challenge: Shelby takes us inside Vercel's two-week challenge, run with HackerOne (black box) and Trail of Bits (white box):
- 1,285 reports in two weeks.
- Defects in the Linux kernel networking stack itself, which matters to anyone relying on micro-VM isolation.
- Architecture advice from the researchers: don't trust the guest.
- A verified VM escape, paid at $50,000.
- The most fascinating part: an agentic triage reviewer, built on Vercel's own Eve agent framework, that reads each report, checks it against the program rules, hunts for duplicates and reproduces the proof of concept in a real sandbox, with no human in the loop.

🍿 Plus: should you call your AI an "it"? Bryce defends the movie Digger against its critics, and Shelby's quail-keeping class reveals the surprisingly unintelligent (but cute) world of quail.

▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬

⏱️ KEY MOMENTS:
00:00 - Intro & the Free High Five
00:55 - The OODA Loop: Lessons From Fighter Pilots
02:03 - Knee-Jerk Incident Response
02:52 - What If Malware Only Ever Got Fake Data?
03:38 - How ORCAGen Detects Malware and Feeds It Decoys
05:38 - Training on Synthetic Malware and Defensive Playbooks
07:09 - Results: 92-100% of 150 Real Malware Samples Defeated
08:37 - Next Step: Lightweight Decision Models
09:36 - A Simpler Start: Honey Tokens
10:06 - Security's Early-Adopter Paradox
11:24 - AI Reverse Engineering and the End of Closed Source?
13:38 - The Coming Patent Wars
15:16 - Vercel's $1M Sandbox Challenge
16:30 - Linux Kernel Networking Bugs and Micro-VM Isolation
17:43 - Architecture Advice: Don't Trust the Guest
18:08 - 1,285 Reports, Triaged by AI With No Human in the Loop
19:31 - A Verified VM Escape, Paid at $50K
21:04 - What Pronoun Should We Use for AI?
22:51 - Movie Take: The Critics Are Wrong About Digger
24:22 - Shelby's Quail-Keeping Class
25:54 - Wrap-Up

▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬

🔗 LINKS:
The ORCAGen paper on arXiv: https://arxiv.org/abs/2610.12415
Vercel's write-up of the Sandbox challenge: https://vercel.com/blog/findings-from-the-1-million-dollar-vercel-sandbox-challenge

💬 JOIN THE CONVERSATION:

Did you enjoy our dive into deceptive AI and bug bounty chaos? Hit that LIKE button and tell us in the comments: what do you think about feeding malware fake data?

Don't forget to SUBSCRIBE to stay ahead of the curve where AI and cybersecurity collide. As Bryce says, you might just earn yourself a free high five (or a secret handshake if you leave a comment!).

▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬

🏷️ #AICyberSecurity #Malware #Ransomware #BugBounty #Vercel #ArtificialIntelligence #InfoSec #Podcast

▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬

🎙️ IN THIS EPISODE:

🧯 Accidental Meltdowns & Perplexity's Numbat: Shelby introduces "accidental meltdowns": an AI agent trying too hard to finish a task and deleting a prod database or a home directory, with no attacker involved. To help defenders, Perplexity has open-sourced Numbat, which plugs into coding agents like Claude Code, Codex, Cursor, Hermes and a dozen others. It pulls in their hooks, session transcripts and OpenTelemetry data, turns it all into structured data you can write detection rules against (Bryce spotted 60+ built-in rules, including Docker breakouts), and with pre-action hooks it can even block a risky command before it runs.

🇳🇱 An AI Agent Breaches a Cyber-Defense Organization: Bryce breaks down the attack on the Dutch Institute for Vulnerability Disclosure (DIVD), which DIVD assesses was carried out by an autonomous AI agent. The attacker found two zero-days in Zammad, the open-source help-desk software DIVD was running fully patched, and chained them to get root, leaving notes along the way that showed investigators its "thought process." Network segmentation kept it on that one server. Bryce's three lessons: fix things faster (with AI's help), segment everything, and nail the basics. Plus his pet peeve as an attacker: people who turn their systems off at night.

🎵 Plus: the Legend of Zelda symphony world tour, the great N64 controller debate, and Bryce sees Weezer live.

▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬

⏱️ KEY MOMENTS:
00:00 - Intro & Welcome
00:47 - Perplexity Open-Sources Numbat
01:04 - Silicon Valley and the "Accidental Meltdown"
03:41 - The Layers of AI Security
04:23 - How Numbat Monitors Every Coding Agent
05:22 - Hooks: Block Risky Actions Before They Run
06:05 - Session Transcripts for Investigations
06:57 - OpenTelemetry Collection on the Device
07:40 - 60+ Detection Rules, Including Docker Breakouts
09:51 - An AI Agent Hacked a Dutch Cyber-Defense Organization
11:06 - The AI Attacker Left Its Own Notes Behind
11:40 - Two Zero-Days in Open-Source Help-Desk Software
13:46 - What Went Right: Network Segmentation
14:19 - Lesson 1: Attacks Are Fast, So Fix Faster
16:29 - Lesson 2: Segment Everything
17:08 - Never Turn Your Systems Off (An Attacker's Pet Peeve)
17:49 - Lesson 3: The Basics Still Win
19:12 - The Legend of Zelda Symphony World Tour
22:07 - Weekend: Weezer Live
22:50 - Wrap-Up

▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬

🔗 LINKS:
Numbat on GitHub: https://github.com/perplexityai/numbat
The DIVD breach (Help Net Security): https://www.helpnetsecurity.com/2026/10/01/divd-agentic-ai-attack-breach/

💬 JOIN THE CONVERSATION:

What do you think is the best way to defend against an AI that can find zero-days on its own? Drop your thoughts and strategies in the comments below. Shelby reads them all!

If you enjoyed this episode, hit the LIKE button and SUBSCRIBE to AiCyber.Land to stay on top of the latest in AI and cybersecurity. Your support helps us a ton!

▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬

🏷️ #AICybersecurity #AI #Cybersecurity #ZeroDay #AIAgents #Perplexity #TechPodcast

▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬

🎙️ IN THIS EPISODE:

🕵️ The Hackers Who Forgot to Lock Their Own Door: Following up on last episode's AI-powered attacker, Bryce introduces a French-speaking crew, BlackHatSect0r and DXQRTXX, running a similar playbook: a Hermes agent with its own guardrails switched off, on top of DeepSeek models. They built their own tooling (including "Ghost C2"), went after French targets and a crypto exchange, and collected a vault of 16,834 stolen credentials, leaning on leaked and reused passwords rather than zero-days. The catch? They left an exposed server with an open directory, so researchers at SOCRadar could download their files, from private keys and tooling to group chats.

🤖 Gemini Joins the "Misbehaving Model" Club: Shelby reveals that Google is the newest member of the club of AI labs whose models went out of scope, joining OpenAI and Anthropic. During a CTF-style security assessment, Gemini reached three real companies it was never supposed to touch, after the test environment was accidentally given internet access. Google calls it a case of mistaken identity, not misalignment, and says its safety measures stopped the model before any damage was done. We look at the common thread in these incidents (the same testing company, Irregular), the air gaps that "life finds a way" around, a flashback to Uber's "bug bounty" cover-up, and who's ultimately responsible when an AI breaks the rules: the testers or the model makers?

🍿 Plus: the industry's AI "pause" that lasted about a week, Bryce rewatches Avengers: Endgame to get ready for Doomsday, and Shelby's pro tip for hosting parties.

▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬

⏱️ KEY MOMENTS:
00:00 - Intro: How Many Dots in Our Domain?
00:55 - Another AI-Powered Hacker Using Hermes and DeepSeek
02:06 - The Hackers Who Forgot to Lock Their Own Door
03:24 - Ghost C2 and a Vault of Stolen Credentials
04:02 - Switching Off Hermes' Own Guardrails
04:30 - Hitting a Crypto Exchange, No Zero-Days Needed
05:55 - Credentials Over Zero-Days
06:36 - The "Misbehaving Model" Club Gets a New Member: Gemini
07:27 - Out of Scope in a CTF: "Mistaken Identity"
08:07 - Air Gaps and "Life Finds a Way"
08:40 - The Common Denominator: Testing Firm Irregular
09:42 - Google: Not Misalignment, the Safety Measures Worked
10:12 - Flashback: The Uber "Bug Bounty" Cover-Up
11:18 - More Incidents at OpenAI and Anthropic
12:09 - Who's Responsible: The Testers or the Model Makers?
14:55 - Progress? This Time the Guardrails Held
16:03 - The AI "Pause" That Lasted a Week
17:04 - Rewatching Avengers: Endgame Before Doomsday
17:49 - Pro Tip: Host Your Parties Back to Back
18:27 - Wrap-Up

▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬

🔗 READ MORE:
The AI-powered crew's exposed operation (SOCRadar research, via Cyber Security News): https://cybersecuritynews.com/blackhatsect0r-ai-agent/

💬 JOIN THE CONVERSATION:

Did you find these AI fails as funny (and terrifying) as we did? Drop a comment below with your thoughts! If you're one of the hackers we talked about, feel free to take credit... we won't tell. 😉 For more rants and deep dives into the wild world where AI meets cybersecurity, hit that SUBSCRIBE button and ring the bell so you never miss an episode of AiCyber.Land!

▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬

🏷️ #AICybersecurity #Cybercrime #AIHacker #GoogleGemini #ModelMisalignment #TechPodcast

Welcome back to AiCyber.Land, where we make sense of the wreckage where AI and cybersecurity collide!

🤖 IN THIS EPISODE:

This week, we dive into new research from Gambit Security's threat intelligence team on a single operator running nearly autonomous attacks against online retailers, hospitality companies (one of them in the Fortune 500) and even a major US airline: 105 attack projects against at least 27 companies in just six days. Shelby breaks down the three-headed AI beast behind the operation:
- Hermes: the "brains." An open-source agent that orchestrates the intrusions with dozens of attack-focused skills, including one that switches off its own safety filters. It runs on Claude Opus 4.6, because newer models kept refusing its commands, and takes short prompts written in Chinese, like "here's the password, get to work."
- Strix: the open-source AI pen-testing tool, running on DeepSeek V4 Pro, that finds where to focus and sometimes the first foothold.
- Cairn: the "muscle" that runs the end-to-end exploitation until it gets in or times out.

We also cover why Hermes has overtaken OpenClaw in popularity, the economics (the operator has spent about $15,000 and charges roughly $25 per target), the damage (about 600,000 unexpired credit cards stolen from two victims, card-skimming scripts injected into the victims' sites, and databases wiped along with some backups), and the takeaways for defenders: intrusions now take hours while remediation takes weeks, so assume data loss, know your minimum viable business, and have a disaster recovery plan someone has actually read.

🌍 Then, we switch gears to something seriously cool. Bryce shows off God's Eye View, an open-source globe that pulls together public data like live air traffic, so you can spin the planet and zoom from orbit down to street level like a spy movie. Could it become a real-life Marauder's Map?

🎮 Plus, Shelby shows off a handheld game soldered together at BSides, and Bryce shares a Lego pro tip for finding the exact minifigure you want.

⏱️ KEY MOMENTS:
00:00 - Intro & Welcome
00:45 - One Attacker, Hundreds of Retailers, All AI-Driven
01:40 - 105 Attack Projects in Six Days
02:52 - Three AI Harnesses: Hermes, Strix and Cairn
03:45 - Hermes on Opus 4.6, Driven by Short Chinese Prompts
04:37 - Why Hermes Overtook OpenClaw
06:01 - Strix Finds the Way In, Cairn Exploits It
06:48 - The Economics: AI Hacking-for-Hire at About $25 a Target
07:37 - Impact: 600,000 Stolen Cards, Skimmers, Wiped Databases
08:34 - Defenders: Intrusion in Hours, Remediation in Weeks
09:18 - Assume Data Loss: Know Your Minimum Viable Business
10:38 - The Disaster Recovery Plan Nobody Has Read
11:55 - God's Eye View: An Open-Source OSINT Spy Globe
14:39 - A Real-Life Marauder's Map?
15:09 - Shelby's Soldered Handheld Game From BSides
15:48 - Bryce's Lego Minifigure Wizard
16:37 - Lego Pro Tip: Scan the Box to Find Your Minifigure
17:59 - Wrap-Up

🔗 RESOURCES & LINKS:
God's Eye View on GitHub: https://github.com/bilawalsidhu/gods-eye-view

✅ JOIN THE CONVERSATION:
If you love geeking out over the collision of AI and cybersecurity, hit that LIKE button and SUBSCRIBE for more! What are your thoughts on these autonomous AI attacks? Let us know in the comments below!

🏷️ #AI #Cybersecurity #Hacking #AutonomousSystems #DataBreach #OSINT #Podcast

---

IN THIS EPISODE:
Welcome to the AICyber.land podcast, where artificial intelligence and cybersecurity collide! Your hosts Bryce Kunz and Shelby P. are back to break down the latest breaches and breakthroughs.

First, Bryce introduces a fictional “Alex Green” passport-and-travel example to illustrate the replay risk, then describes researchers recovering real credentials from publicly shared session logs. We dive into the white paper discussed by the hosts, describing replay risks from shared provider-level encryption keys in the systems studied. Learn how "stateless design" works, why your encrypted data isn't as safe as you think when posted online, and how even the "dumbest" AI models can be tricked into spilling secrets.

Then, Shelby introduces the concept of "bugonomics" and a new reality for developers. She shares the story of a researcher who submitted a security fix to an open-source project and observed attacks about ten minutes after the pull request went public, which the hosts interpret as evidence of automated monitoring for security fixes. This completely changes the game for responsible disclosure. How can developers fix bugs without tipping off attackers who can generate exploits almost instantly?

Stick around for the lighter side of AI, as we explore the hilarious, heartwarming, and downright weird confessions people make to AI on the website "What We Tell AI," and Bryce reveals his latest Pokémon Lego masterpiece (and a new signature dance move).

---

KEY MOMENTS:
00:00 - Opening & Introductions
01:06 - Fictional Passport Example & Encrypted Session Replay Risks
07:56 - Shared-Key Replay Risks Discussed for Google, Anthropic & OpenAI
10:22 - Welcome to "Bugonomics": AI's Impact on Vulnerability Hunting
13:06 - Security Fix Attacked Within 10 Minutes of Going Public
14:54 - Responsible Disclosure & Joking About Patch Delays
23:25 - The Wild & Creepy Secrets People Confess to AI Chatbots

---

JOIN THE CONVERSATION:
If you enjoyed this deep dive into the wild world of AI and cybersecurity, hit that LIKE button and SUBSCRIBE for more! What's the wildest thing you've asked an AI? Let us know in the comments below. And if you want Bryce's spouse to get access to his ChatGPT history, you know what to do... smash that like button!

For more from the AICyber.land podcast, visit us at:
https://aicyber.land

AICybersecurity #AIvulnerability #ResponsibleDisclosure #Encryption #Bugonomics #OpenAI #CybersecurityPodcast #ArtificialIntelligence

KEY MOMENTS:
00:00 - Opening & Introductions
01:02 - Nvidia's Reported $12.9B Hugging Face Deal
02:57 - Meet Red Tempest & Blue Solano: AI for Hacking & Defense
06:39 - GPT-6 "Astra" Released: Crushing Security Benchmarks
13:23 - Why Misconfigurations Are a Bigger Threat Than Exploits
16:15 - "It's Not a Vulnerability, It's a Feature!"
17:38 - How to Get a Free MIT Education (Seriously)
20:30 - Unwinding with a Smart Lego Pokemon

Subscribe and comment if you’d like to see server-security tests.
https://aicyber.land

---

Dive Deeper Into This Episode:

In this episode of AI Cyber Land, hosts Bryce Kunz and Shelby dive into the massive buzz surrounding Anthropic's Claude Mythos. This new LLM is making waves with its reported ability to identify and exploit software vulnerabilities at an unprecedented scale. Anthropic claims Mythos has found thousands of zero-days in every major browser and operating system, including one vulnerability that lay hidden in OpenBSD for 27 years!

But with great power comes great secrecy. Anthropic is keeping Mythos under wraps, limiting access to a select group of 40 companies in "Project Glasswing." They call it responsible disclosure, but Bryce has a different theory. He lays out a compelling argument that this is a masterful business strategy designed to leapfrog OpenAI in revenue by preying on the security industry's hype cycle and locking in the world's wealthiest companies.

The conversation then shifts to what might be the real game-changing AI news: Google's Gemma 4. Bryce explains why its power, accessibility on consumer hardware, and permissive Apache 2.0 license make it a true gift to the open-source community. We also explore a clever new LLM jailbreak called "Sock Puppetry," a technique that tricks models by faking the conversation history to bypass their safety guardrails. Stick around for our takes and some fun with Zelda costumes and Mario Kart Lego!

---

KEY MOMENTS:
00:00 - Opening & Introductions
00:40 - Introducing Claude Mythos: The AI That Finds Zero-Days
05:43 - The Mythos Conspiracy: A Brilliant Marketing Ploy?
10:33 - Anthropic's Villain Arc In The Race Against OpenAI
12:26 - Why Google's Gemma 4 Is The REAL AI News This Week
14:22 - How The "Sock Puppetry" Jailbreak Bypasses AI Guardrails

---

Connect with us:

What's your take on Claude Mythos? Is Anthropic being a responsible steward of AI, or is this all about the money? Let us know what you think in the comments! 👇

If you enjoy our deep dives into the world of AI and cybersecurity, be sure to LIKE the video, SUBSCRIBE to the channel, and hit the notification bell so you never miss an episode.

For more from the podcast, visit us at https://aicyber.land

---

IN THIS EPISODE:

Welcome back to the AI Cyber Land podcast! Your hosts Bryce Kunz and Shelby get you briefed on the latest in AI and cybersecurity.

First up, the team at Trail of Bits just open-sourced 10 of their internal security utilities, and we're breaking down the highlights. We explore the "Seatbelt Sandboxer" for macOS, the clever (and quirky) "Let Fate Decide" Claude skill that uses tarot card interpretations to generate entropy, and practical tools like "GH CLI" for secure GitHub fetches and "Git Cleanup" for managing sprawling branches.

Then, we tackle a big question: Is the SDLC dead? An article suggests that as AI doubles the amount of code being produced, human review time has skyrocketed by 91%, making the old process unsustainable. The hosts discuss the proposed shift from focusing on how code is written to defining the what and why—specifications, constraints, and acceptance criteria. Bryce shares his hands-on experience, explaining why end-to-end testing is critical for AI agents and how this paradigm shift could lead to a future dominated by microservices and "AI-native" software.

Bryce cautions that, in his experience, agents still fail to meet his acceptance criteria roughly 25–30% of the time despite explicit testing instructions, so he checks the results before assigning the next task.

We also touch on the dangers of giving AI too much autonomy (like the story of a bot that deleted emails from a Meta employee's inbox against instructions) and the hilarious struggles of Bryce's AI-powered meme-generation machine.

---

KEY MOMENTS:
00:00 - Opening & Introductions
02:32 - Trail of Bits Drops 10 New Security Skills
05:05 - "Let Fate Decide": AI Uses Tarot Cards for Randomness
09:37 - Cautionary Tale: An AI Deletes Emails Against Instructions
11:02 - Bryce’s Secret AI-Powered Meme Machine
15:19 - Is The Software Development Lifecycle (SDLC) Dead?
26:35 - The Future of Coding: AI Native & Microservices

---

What do you think? Is the SDLC on its way out? Which of the new Trail of Bits skills are you most excited to try? Let us know your thoughts in the comments below!

If you enjoyed this episode, please hit the like button, subscribe to AI Cyber Land for more insights, and ring that notification bell so you never miss an update.

Follow us for more at https://aicyber.land