This week in the Wild West roundup:

2026-03-30 · Bits and Bobs 3/30/26

This week in the Wild West roundup:
- Claude Extension Flaw Enabled Zero-Click XSS Prompt Injection via Any Website
- OpenClaw Agents Can Be Guilt-Tripped Into Self-Sabotage.
  - "In a controlled experiment, OpenClaw agents proved prone to panic and vulnerable to manipulation.
  - They even disabled their own functionality when gaslit by humans."
  - Say it again now, "LLMs shouldn't be trusted to make security decisions!"
- Zenity CTO demos 0-click AI agent exploits on stage at RSAC
- Seeking Alpha: OpenClaw is a Liability Not Breakthrough, as Frenzy Suggests.
  - Even non-tech outlets are realizing that OpenClaw is powerful because it's dangerous.
- ZombieClaw: The AI Botnet Nobody Is Talking About.
  - Sketches out how OpenClaw could be turned into a new kind of super botnet.

More on this topic

From other episodes