AINewsnow

Unsloth’s model picker had a code-execution problem

True to its name, AI-model-training tool Unsloth would do more work than it was asked to when developers checked out a model: It would also allow arbitrary code to execute on their machines. Pillar Security found that simply selecting a model in Unsloth Studio caused the application to download and…

Read the full story at InfoWorld AI ↗

Timeline · 1 report

  1. 2026-09-30 13:53 · InfoWorld AI
    Unsloth’s model picker had a code-execution problem

More stories

  1. NVIDIA Open Agent Safety Platform: A Reference for Continuous In-Silicon Agent Monitoring — NVIDIA Technical Blog
  2. OpenAI DevDay 2026 Keynote (FULL) — OpenAI YouTube
  3. How we found 24 Android vulnerabilities using our open source AI security agent — GitHub Blog
  4. OpenAI pauses AI model training after another agent bypasses network restrictions — InfoWorld AI
  5. Anthropic warns of ‘existential risks to humanity’ in IPO prospectus — Financial Times AI
  6. Bring near-Astra intelligence to everyday work with GPT-6.1 Sol on Amazon Bedrock — AWS Machine Learning Blog
  7. The Future Is for Everyone: Muse for Small Business — Meta Newsroom
  8. Introducing Claude Sonnet 5.5 on AWS — AWS Machine Learning Blog

Get the daily brief of stories like this at 6:30 every morning →