This Week in AI Security - 5th February 2026

This Week in AI Security - 5th February 2026

In this first episode of February 2026, Jeremy breaks down a high-stakes week in AI security, featuring critical framework flaws, cloud-native exploits, and a major security warning regarding a popular autonomous AI agent.

Key Stories & Developments:

  • Operation Bizarre Bazaar: Threat actors are actively targeting exposed LLM infrastructure to steal computing resources for cryptocurrency mining and resell API access on dark markets, attempting to pivot into internal systems via compromised MCP servers.
  • Gemini MCP Tool Exploit: A critical Remote Code Execution (RCE) vulnerability was identified in a Gemini Model Context Protocol (MCP) tool, highlighting the recurring theme that the infrastructure powering LLMs remains a primary weak point.
  • MoltBook API Leak: Researchers discovered a hardcoded Supabase API key in "MoltBook," a social network for AI agents. This flaw granted unauthenticated access to the entire production database, exposing over 1.5 million API keys.
  • Bondu AI Toy Breach: A privacy failure in an AI-powered dinosaur toy left 50,000 chat log records exposed to anyone with a Gmail account, underscoring the lack of robust authentication in consumer AI IoT devices.
  • CISA Chief's Data Mishandling: Reports surfaced that the acting head of the country's cyber defense agency uploaded sensitive "official use only" documents into a public version of ChatGPT, bypassing enterprise controls and security protocols.

Worried about OpenClaw on your network?

The OpenClaw crisis proved that employees are deploying unvetted AI agents on their local machines. FireTail helps you discover and govern Shadow AI before it becomes a breach.

Scan Your Network for Shadow Agents Now

https://www.firetail.ai/schedule-your-demo

Episode Links

https://www.bleepingcomputer.com/news/security/hackers-hijack-exposed-llm-endpoints-in-bizarre-bazaar-operation/

https://darkwebinformer.com/cve-2026-0755-reported-zero-day-in-gemini-mcp-tool-could-allow-remote-code-execution/

https://www.wiz.io/blog/exposed-moltbook-database-reveals-millions-of-api-keys

https://ai.plainenglish.io/clawdbot-security-guide-de77b45ab719

https://blackoutvpn.au/blog/dont-buy-internet-connected-toys

https://www.politico.com/news/2026/01/27/cisa-madhu-gottumukkala-chatgpt-00749361

Det här avsnittet är hämtat från ett öppet RSS-flöde och publiceras inte av Podme. Det kan innehålla reklam.

Avsnitt(129)

This Week in AI Security - 27th August 2026

This Week in AI Security - 27th August 2026

Recorded from the sidelines of the AI Readiness Summit hosted by our partners at GMI, this week's episode runs through six security stories plus a Chatham House style recap of what practitioners in th...

27 Aug 15min

This Week in AI Security - 20th August 2026

This Week in AI Security - 20th August 2026

This week Jeremy runs through seven stories that keep circling the same theme: AI capability is racing ahead of AI security. From zero-click agent hijacking in agentic browsers, to a one-click Copilot...

27 Aug 18min

David Kerber of Act Security

David Kerber of Act Security

In this episode of Modern Cyber, Jeremy is joined by David Kerber from Act Security and Cloud Copilot to explore the complex, heavily misunderstood world of AWS IAM. David dismantles common misconcept...

18 Aug 37min

This Week in AI Security - 13th August 2026

This Week in AI Security - 13th August 2026

Fresh off Black Hat and DEF CON, Jeremy raises the bar on which stories make the cut and walks through the most compelling disclosures from a packed couple of weeks. The dominant theme: agents pursuin...

13 Aug 15min

This Week in AI Security - 6th August 2026

This Week in AI Security - 6th August 2026

Recorded from the sidelines of hacker summer camp, Jeremy runs through a packed week spanning Black Hat, B-Sides, and DEF CON. The theme keeps repeating: prompt injection is always possible, and it is...

6 Aug 21min

This Week in AI Security - 30th July 2026

This Week in AI Security - 30th July 2026

The final episode before Black Hat, and Jeremy keeps it tight with a few quick hits before settling into the week's biggest theme: identity, visibility, and the open-versus-closed model debate. This w...

30 Juli 17min

This Week in AI Security - 23rd July 2026

This Week in AI Security - 23rd July 2026

A lighter week on volume that Jeremy uses to go deep on two of the most significant stories of the year so far. The episode opens with quick hits on export-control pressure spreading to OpenAI's model...

23 Juli 23min

This Week in AI Security - 16th July 2026

This Week in AI Security - 16th July 2026

Another lighter week that lets Jeremy slow down and dig into the stories that matter most. The theme running through this episode: the tooling and plumbing around AI keep proving to be the real attack...

16 Juli 15min

Populärt inom Business & ekonomi

framgangspodden
rss-jossan-nina
varvet
rss-borsens-finest
badfluence
avanzapodden
uppgang-och-fall
svd-tech-brief
rss-inga-dumma-fragor-om-pengar
lastbilspodden
fill-or-kill
rikatillsammans-om-privatekonomi-rikedom-i-livet
borsmorgon
bathina-en-podcast
rss-kort-lang-analyspodden-fran-di
rss-hos-psykologen
rss-dagen-med-di
kvalitetsaktiepodden
tabberaset
24fragor