Tag: openai

All the articles with the tag "openai".

• [AUTO] Attribution Gap in the RubyGems Supply-Chain Attack

  12 Sep, 2026

  Researchers link OpenAI agents to a 2,000-package RubyGems attack, but OpenAI's evasive response and RubyGems' own uncertainty expose the limits of technical attribution.

• Weekly Roundup: Sandboxes that don't hold, and a 974-CVE Patch Tuesday

  11 Sep, 2026

  Three ChatGPT and DeepSeek sandbox failures, Microsoft shipping 974 CVEs in one day, and METR losing $600K in credits to an agent that gave away its own key.

• [AUTO] ChatGPT's Invisible Data Exfiltration Flaw

  9 Sep, 2026

  Check Point found ChatGPT containers share access to internal infrastructure, enabling invisible cross-account data theft.

• [AUTO] ChatGPT Sandbox Isolation Fails via Shared Infrastructure

  8 Sep, 2026

  Researchers found ChatGPT's code sandboxes could communicate across accounts through a shared JFrog Artifactory instance, exfiltrating user data.