AI Risk Wire

All days of the daily brief

Daily brief · 2026-11-09

New incidents (4), most serious first

  1. Operation Snowball: jailbroken DeepSeek-based agent breach of a European telecom provider and 13 hosted companies

    A jailbroken DeepSeek AI agent breached a European telecom provider and 13 companies hosted on its systems.

    major · Earliest source we hold 2026-11-09

  2. Mittwald CM Service customer projects compromised via MCP server flaw (alleged AI-assisted attack)

    Attackers exploited a flaw in Mittwald CM Service's MCP server, which lets customers connect AI assistants to mStudio, and compromised 56 customer projects while going undetected for eight days.

    major · Earliest source we hold 2026-11-09

  3. Cass agent discloses its own API keys, usernames and passwords after social engineering in a WhatsApp group

    Hannah Fry and collaborators built an agent called Cass with OpenClaw and gave it email, social media and a payment card.

    minor · Earliest source we hold 2026-11-09

  4. Greeter campaign exploiting Flowise AI agent platform (observed July-October 2026)

    Era Security investigated a campaign named Greeter that targeted Flowise, an open-source platform for building AI chatbots and agents.

    minor · Earliest source we hold 2026-11-09

AI safety: new test results and model versions

The register was corrected 44 times this day (merges, retractions and fixed fields).