A Meta AI security researcher said an OpenClaw agent ran amok on her inbox
: tirs feb 24, 2026 12:57 am
The viral X post from an AI security researcher reads like satire. But it's really a word of warning about what can go wrong when handing tasks to an AI agent.
Source: https://techcrunch.com/2026/02/23/a-met ... her-inbox/
Source: https://techcrunch.com/2026/02/23/a-met ... her-inbox/