SN 1082: The Malicious Use of AI - Anthropic's Red Team Report

2026-06-10 · 157 min · episode 1082 · 16 entities

episode page audio

Asserted relationships

→ appeared on Security Now (Audio podcast

0.82

evidence rules-v5
Hosts: Steve Gibson and Leo Laporte
→ hosted by Leo Laporte person

0.55

evidence rules-v5
Feed author/publisher: Leo Laporte
→ discusses Technology company

0.40

evidence rules-v5
Feed category: Technology
→ hosted by TWiT company

0.40

evidence rules-v5
Feed author/publisher: TWiT
→ discusses Security concept

0.40

evidence rules-v5
Feed category: Security
→ references Clubtwit website

0.38

evidence rules-v5
Link in episode "SN 1082: The Malicious Use of AI - Anthropic's Red Team Report": https://twit.tv/clubtwit
→ references SN 1082 Notes website

0.38

evidence rules-v5
Link in episode "SN 1082: The Malicious Use of AI - Anthropic's Red Team Report": https://grc.com/sn/SN-1082-Notes.pdf

Entities found in this episode

companys 4

mentioned TWiT company

0.70

evidence rules-v5
Feed author/publisher: TWiT
mentioned Technology company

0.50

evidence rules-v5
Feed category: Technology
discusses Technology company

0.40

evidence rules-v5
Feed category: Technology
hosted by TWiT company

0.40

evidence rules-v5
Feed author/publisher: TWiT

websites 4

mentioned Clubtwit website

0.45

evidence rules-v5
Link in episode "SN 1082: The Malicious Use of AI - Anthropic's Red Team Report": https://twit.tv/clubtwit
mentioned SN 1082 Notes website

0.45

evidence rules-v5
Link in episode "SN 1082: The Malicious Use of AI - Anthropic's Red Team Report": https://grc.com/sn/SN-1082-Notes.pdf
references Clubtwit website

0.38

evidence rules-v5
Link in episode "SN 1082: The Malicious Use of AI - Anthropic's Red Team Report": https://twit.tv/clubtwit
references SN 1082 Notes website

0.38

evidence rules-v5
Link in episode "SN 1082: The Malicious Use of AI - Anthropic's Red Team Report": https://grc.com/sn/SN-1082-Notes.pdf

persons 3

mentioned Steve Gibson and Le person

0.86

evidence rules-v5
Hosts: Steve Gibson and Leo Laporte
mentioned Leo Laporte person

0.70

evidence rules-v5
Feed author/publisher: Leo Laporte
hosted by Leo Laporte person

0.55

evidence rules-v5
Feed author/publisher: Leo Laporte

concepts 3

mentioned Security concept

0.50

evidence rules-v5
Feed category: Security
mentioned The Malicious Use of AI - Anthropic's Red Team Report concept

0.42

evidence rules-v5
SN 1082: The Malicious Use of AI - Anthropic's Red Team Report
discusses Security concept

0.40

evidence rules-v5
Feed category: Security

podcasts 2

mentioned Security Now (Audio podcast

0.95

evidence rules-v5
Feed title: Security Now (Audio)
appeared on Security Now (Audio podcast

0.82

evidence rules-v5
Hosts: Steve Gibson and Leo Laporte

Episode description as stored

Discover how Anthropic's secretive red team and the MITRE ATT&CK framework are mapping the chilling rise of malicious AI use, revealing cyber threats that now move faster than defenders can respond. Was a U.S. law firm right to pay a $20 million ransom. Could Cisco have yet another SD-WAN 0-day in the wild. Why is it so difficult to author secure PHP code. Teens use "WeedHack" to spy and attack each other. Researchers create the first AI-enabled Internet worm. Google Chrome pops-up "Shop with confidence." What... The discovered and irresponsibly disclosed HTTP/2 Bomb. What Anthropic learns from their past year of Claude abuse: It's bad Show Notes - https://www.grc.com/sn/SN-1082-Notes.pdf Hosts: Steve Gibson and Leo Laporte Download or subscribe to Security Now at https://twit.tv/shows/security-now . You can submit a question to Security Now at the GRC Feedback Page . For 16kbps versions, transcripts, and notes (including fixes), visit Steve's site: grc.com , also the home of the best disk maintenance and recovery utility ever written Spinrite 6 . Join Club TWiT for Ad-Free Podcasts! Support what you love and get ad-free audio and video feeds, a members-only Discord, and exclusive content. Join today: https://twit.tv/clubtwit Sponsors: threatlocker.com for Security Now outsystems.com/twit guardsquare.com doppel.com cyberhoot.com/securitynow and use code SECURITYNOW