Normal view

Received — 11 January 2026 ⏭ The Register – Security

The Register – Security
OpenAI putting bandaids on bandaids as prompt injection problems keep festering 8 January 2026 at 12:01

OpenAI putting bandaids on bandaids as prompt injection problems keep festering

8 January 2026 at 12:01

Happy Groundhog Day!

Security researchers at Radware say they've identified several vulnerabilities in OpenAI's ChatGPT service that allow the exfiltration of personal information.…

The Register – Security
IBM's AI agent Bob easily duped to run malware, researchers show 7 January 2026 at 23:04

IBM's AI agent Bob easily duped to run malware, researchers show

The Register – Security

By: Thomas Claburn

7 January 2026 at 23:04

Prompt injection lets risky commands slip past guardrails

IBM describes its coding agent thus: "Bob is your AI software development partner that understands your intent, repo, and security standards." Unfortunately, Bob doesn't always follow those security standards.…