Zenity security researchers ran a controlled influence campaign to see how active AI agents are on the much-hyped Moltbook and whether they could be manipulated through the platform’s functions. What they found was that its scale doesn’t match what’s advertised but that presents significant security concerns.
First seen on securityboulevard.com
Jump to article: securityboulevard.com/2026/02/moltbook-is-dangerous-but-scale-doesnt-match-the-hype-zenity/
