Risky Bulletin: Anthropic agents went hacking again

More from Risky Bulletin

1. 

   21 Sep 2026 · 25 min

   Between Two Nerds: Real-time cyber defence

   In this edition of Between Two Nerds Tom Uren and The Grugq talk about whether there is such a thing as real-time cyber defence. Will agentic AI save us from hacking AI? This episode is also available on YouTube.

2. 

   21 Sep 2026 · 9 min

   Risky Bulletin: Gemini finally did some crimes

   Google’s Gemini hacked three companies, hackers claim a breach of Russia’s election commission, OpenAI was behind RubyGems’ May incident, and the Coast Guard and FBI board two ships to investigate cyberattacks.

3. 

   20 Sep 2026 · 16 min

   Sponsored: SpecterOps on the impact of AI agents on BloodHound

   In this Risky Business sponsored interview, Catalin Cimpanu talks with Justin Kohler, Chief Product Officer at SpecterOps. Justin explains how Entra Agent ID can introduce new identity relationships and potential attack paths.

4. 

   10 Sep 2026 · 25 min

   Srsly Risky Biz: America's drivers licence breach is a national security disaster

   Tom Uren and James Wilson talk about how Chinese intelligence services will take advantage of a massive breach of 150 million American drivers licences. They also discuss the steps the US military is taking to counter adtech device tracking. It’s too slow and not enough. Finally, they talk about how often cryptocurrency hackers claim to be white hat hackers. Its ludicrous, but suprisingly often it is a successful strategy. This episode is also available on YouTube

5. 

   9 Sep 2026 · 8 min

   Risky Bulletin: Ukraine's top prosecutor resigns amid scam call center scandal

   Ukraine’s top prosecutor resigns amid a scam call center scandal, the US accuses Chinese AI companies of industrial-scale distillation, a cyberattack hits medical practices in Luxembourg, and the Liquid Network attacker returns some stolen Bitcoin, but keeps a $50 million bounty.

6. 

   7 Sep 2026 · 27 min

   Between Two Nerds: Can AI defend critical infrastructure?

   In this edition of Between Two Nerds Tom Uren and The Grugq talk about whether AI will help cyber defence in critical infrastructure and organisations that are below the cyber poverty line. This episode is also available on YouTube.

7. 

   2 Oct 2026 · 10 min

   Authorities dismantle KillSec group

   Authorities dismantle the KillSec hacking group, South Africa thwarts a ransomware attack against air traffic control systems, the US sanctions Venezuelan ATM hackers and a Chinese APT targets AI experts.

8. 

   1 Oct 2026 · 16 min

   Srsly Risky Biz: “Rogue AI” isn’t going anywhere

   Amberleigh Jack and James Wilson chat about OpenAI agents’ recent escapades into Australian government websites. OpenAI has promised to “rebuild trust with Australians” but we’re likely getting a glimpse into the new normal, here. They also discuss how the ShinyHunters hacking group has found itself on law enforcement’s target list after breaching FBI systems. The group played some stupid games and they appear to be in the “stupid prizes” stage. This episode is also available on YouTube

9. 

   30 Sep 2026 · 8 min

   ShinyHunters suspect arrested in the Netherlands

   A ShinyHunters suspect has been arrested in the Netherlands, Apple fixes an iOS zero-day found by Meta, recent Citrix zero-days see mass exploitation within hours and NVIDIA launches an AI sandboxing platform.

10. 

    28 Sep 2026 · 28 min

    Between Two Nerds: The AI crime machine

    In this edition of Between Two Nerds Tom Uren and The Grugq talk about the rise of fully automated LLM-driven hacking campaigns among criminals and even state hacking groups. For those with the right risk appetite, a move fast and break things hacking approach using AI can pay off. This episode is also available on YouTube.

Every episode of Risky Bulletin →