loader from loading.io

AI Agent Hacks McKinsey Chatbot in 2 Hours

Cybersecurity Today

Release Date: 03/13/2026

RSAC Presenter Says RSAC Presenter Says "Time to Kill One of Cybersecurity's Most Overworked Terms"

Cybersecurity Today

RSAC: Retiring “APT,” FCC’s US-Made Router Ban, Zoom Call Scraping, Iran-Targeting Wiper, and Cyber Terrorism Insurance From RSAC 2026, host David Shipley highlights ESET researcher Robert Lipowsky’s argument to retire the overused “advanced persistent threat” label and instead describe actors by motivation and activity, noting blurred lines between nation-state and criminal tooling. He also reports RSAC vendor trends (zero trust fading, “agentic AI” everywhere) and standout booth themes. In Washington, the FCC bans authorization of any new Wi‑Fi router models not made in the...

info_outline
Startup Accused Of Helping Fake Privacy and Security Audits show art Startup Accused Of Helping Fake Privacy and Security Audits

Cybersecurity Today

Compliance Startup Audit-Faking Claims, Trivy Supply-Chain Backdoor, Russia Targets Signal/WhatsApp, and Iran-Linked Stryker Disruption Cybersecurity Today  would like to thank Meter for their support in bringing you this podcast. Meter delivers a complete networking stack, wired, wireless and cellular in one integrated solution that's built for performance and scale.  You can find them at Meter.com/cst This episode covers allegations that Y Combinator-backed compliance startup Delve helped customers fake privacy and security audits by generating fabricated evidence that auditors...

info_outline
The Fundamental Mistake in Cybersecurity Risk Management show art The Fundamental Mistake in Cybersecurity Risk Management

Cybersecurity Today

Cybersecurity Isn’t Managing Risk—It’s Managing Threats... And That's the Problem Host David Shipley speaks with Jeff Gardiner, a former university CISO and now at Morgan Stanley, about Gardiner’s doctoral research arguing that cybersecurity has structurally misclassified “risk management” as threat management.  Gardiner explains that real risk is an expected loss calculation (impact × likelihood), while many cybersecurity frameworks and training emphasize vulnerabilities, exploitability, and system configuration without likelihood or business impact. He describes examples...

info_outline
FBI Seizes Iran-Linked Handala Leak Site After Stryker Intune Wipe Attack: Cybersecurity Today show art FBI Seizes Iran-Linked Handala Leak Site After Stryker Intune Wipe Attack: Cybersecurity Today

Cybersecurity Today

FBI Seizes Iran-Linked Handala Leak Site After Stryker Intune Wipe Attack; Apple iPhone Exploit Patch; North Korean Fake IT Workers Grow Cybersecurity Today  would like to thank Meter for their support in bringing you this podcast. Meter delivers a complete networking stack, wired, wireless and cellular in one integrated solution that's built for performance and scale.  You can find them at Meter.com/cst The episode reports that the FBI has seized the data leak site used by the Iran-linked hacktivist group Handala, which has been widely linked to the Stryker attack where attackers...

info_outline
Another Medical Device Firm Hit show art Another Medical Device Firm Hit

Cybersecurity Today

Medical Device Breaches, Anti-Scam Pledge Scrutiny, AI Font Trick, and Iran-Linked Cyber Updates. Cybersecurity Today  would like to thank Meter for their support in bringing you this podcast. Meter delivers a complete networking stack, wired, wireless and cellular in one integrated solution that's built for performance and scale.  You can find them at Meter.com/cst The episode covers several cybersecurity stories: Intuitive Surgical disclosed a March 12 phishing-led intrusion where stolen credentials enabled access to its internal administrative network and data theft...

info_outline
Notorious Hacker Group Notorious Hacker Group "The Comm," Operation Synergia Takedown, Stryker Cyberattack Update & More

Cybersecurity Today

Alleged Canadian ‘The Comm’ Hacker Arrested, Interpol’s Operation Synergia Takedown, Stryker Cyberattack Update and more.. Cybersecurity Today  would like to thank Meter for their support in bringing you this podcast. Meter delivers a complete networking stack, wired, wireless and cellular in one integrated solution that's built for performance and scale.  You can find them at Meter.com/cst Host David Shipley covers new details on the alleged takedown of “Waifu,” a Canadian hacker tied to the cybercrime group The Com, after a harassment campaign against investigator Allison...

info_outline
AI Anxiety: Cybersecurity Today with Special Guest Krish Banerjee, Managing Director (Partner) & Canada Lead - Data & AI - Accenture show art AI Anxiety: Cybersecurity Today with Special Guest Krish Banerjee, Managing Director (Partner) & Canada Lead - Data & AI - Accenture

Cybersecurity Today

Gemini in Google Workspace, Agentic AI, and Managing AI Anxiety (with Accenture’s Krish Banerjee) Cybersecurity Today  would like to thank Meter for their support in bringing you this podcast. Meter delivers a complete networking stack, wired, wireless and cellular in one integrated solution that's built for performance and scale.  You can find them at Meter.com/cst In a special edition of Project Synapse shared with Cybersecurity Today, host Jim Love and co-host John Pinard (a VP and CSO at a Canadian financial institution) speak with Krish Banerjee, Accenture’s managing...

info_outline
AI Agent Hacks McKinsey Chatbot in 2 Hours show art AI Agent Hacks McKinsey Chatbot in 2 Hours

Cybersecurity Today

AI Agent Hacks McKinsey Chatbot in 2 Hours, NPM Phantom Raven, Router Malware & Trojaned AI Models This episode covers how researchers at CodeWall used an autonomous AI security agent to gain read/write access to McKinsey’s internal chatbot Lilli database in about two hours by chaining exposed APIs and an SQL injection, potentially exposing 46.5 million chats, 728,000 files, 57,000 accounts, and 95 system prompts, with McKinsey saying the issues were fixed and no unauthorized access was found. It also reports on the Phantom Raven supply-chain campaign that published 88 malicious NPM...

info_outline
Cyber Security Today Special Report:  Attack from Iran show art Cyber Security Today Special Report: Attack from Iran

Cybersecurity Today

This includes our regular Wednesday/Thursday segment but with an update from this breaking story on the attack on a large US medical company.

info_outline
Fake Claude Code Installs, Arpa Phishing, Iranian and Russian Teams Mount Cyber Retaliation show art Fake Claude Code Installs, Arpa Phishing, Iranian and Russian Teams Mount Cyber Retaliation

Cybersecurity Today

Fake Claude Code Installs, Arpa Phishing, Zombie ZIP Malware Evasion, and Iran/Israel Cyber Retaliation This episode covers four major security stories: the “InstaFix” campaign using Google sponsored ads and cloned Claude Code install pages to trick developers into pasting terminal commands that deploy the TeraStealer credential-stealing malware; a phishing technique abusing the special-use .arpa domain and IPv6 reverse DNS to evade email and domain-based defenses, using attacker-controlled DNS zones, traffic distribution systems, and lures like surveys and account notices; the “Zombie...

info_outline
 
More Episodes

AI Agent Hacks McKinsey Chatbot in 2 Hours, NPM Phantom Raven, Router Malware & Trojaned AI Models

This episode covers how researchers at CodeWall used an autonomous AI security agent to gain read/write access to McKinsey’s internal chatbot Lilli database in about two hours by chaining exposed APIs and an SQL injection, potentially exposing 46.5 million chats, 728,000 files, 57,000 accounts, and 95 system prompts, with McKinsey saying the issues were fixed and no unauthorized access was found. It also reports on the Phantom Raven supply-chain campaign that published 88 malicious NPM packages using a runtime-downloaded payload to steal developer system data like SSH keys and host details. A study warns that 83% of 800 million compromised passwords still meet complexity rules, highlighting credential-stuffing risk and the need for breach checks and MFA. The show notes 14,000+ routers infected with persistent malware often requiring factory resets plus hardening, and discusses Trojan backdoors embedded in AI models that trigger misbehavior under specific inputs, calling for new AI security testing and validation.

Cybersecurity Today  would like to thank Meter for their support in bringing you this podcast. Meter delivers a complete networking stack, wired, wireless and cellular in one integrated solution that's built for performance and scale.  You can find them at Meter.com/cst

00:00 Sponsor Meter Intro
00:20 Headlines And Welcome
00:55 AI Agent Hacks McKinsey Bot
03:44 Phantom Raven NPM Malware
05:55 Strong Passwords Still Leaked
07:55 Router Malware That Persists
09:36 Trojan Backdoors In AI Models
12:01 Call For AI Backdoor Research
12:30 Sponsor Meter Outro
13:13 Sign Off