LIVE FEED
HIGH Fireworks AI Breach Exposes Notion AI Chat Transcripts // FIRST LOOK OpenAI Launches AI-Powered Security Sprint with Cathedral Systems // FIRST LOOK Google DeepMind AI Agents Accelerate Cryptographic Vulnerability Research // HIGH BOSSAI AI Agents Used to Breach Taipei Emergency Dispatch Systems // FIRST LOOK NVIDIA OpenShell Brings Sandboxed Runtime to Secure AI Agents // FIRST LOOK Axiom Math Launches Formally Verified AI Math Foundation in Lean // HIGH ChatGPT Lockdown Mode Bypassed to Exfiltrate Chats Silently // FIRST LOOK Microsoft Ships Dynamic Permissions and Execution Containers for AI Agents // CRITICAL ARTEX Agentic Hacking Platform Drives Autonomous RCE Attacks // FIRST LOOK OpenAI Partners with Hacktron to Find Vulnerabilities in AI Systems //
Fireworks AI Breach Exposes Notion AI Chat Transcripts

Fireworks AI Breach Exposes Notion AI Chat Transcripts

ATLAS OWASP HIGH Significant risk · Prioritise patching ▲ 7.5 HN AI Security

A security breach at Fireworks AI, a third-party inference and classification provider, has resulted in the exposure of unattributable Notion AI chat transcripts affecting less than 1% of Notion workspaces. Malicious actors accessed potential customer data, confirmed by Fireworks on November 8, 2026, including chat sessions used for Notion's AI Insights feature. While the exposed data lacked direct user or workspace identifiers, the incident highlights significant supply chain risks inherent in delegating AI inference and classification workloads to external vendors.

◉ AI THREAT BRIEFING

Stay ahead of the threat.

Twice-weekly digest of critical AI security developments — every story mapped to MITRE ATLAS and OWASP LLM Top 10. Free.

No spam. Unsubscribe anytime.