This week's Wild West roundup:

2026-09-21 · Bits and Bobs 9/21/26

This week's Wild West roundup:
- BragJack Attack Can Turn a Browser's Agentic AI Against It
  - "A new type of attack hijacks the AI assistant built directly into various browsers to access sensitive information, execute malicious actions, and exfiltrate data."
- LLMs respond differently to harmful prompts when AI watermarking is used
  - "SynthID can cause models to follow harmful instructions they would otherwise refuse."
- OpenAI discovered Self-generated prompt injections in compaction summaries.
  - The models were prompt-injecting themselves!
- Human Attacker Hits Machine-Speed Exploitation of Marimo RCE.
- Google Research: OpenClaw in the Wild: Security Analysis of Autonomous Agents.
- Sarah Sanders: The AI Agent With 'Hands' Is Structurally Indistinguishable From Malware.

More on this topic

From other episodes