NanoClaw and JFrog launch 'immune system' to block AI agents from downloading malicious code

NanoClaw and JFrog launched a security integration that routes NanoClaw autonomous agents through JFrog’s scanned software registries, limiting downloads to vetted dependencies. The companies say the tool addresses a growing risk as AI agents install packages in the background without clear human oversight.

The partnership reflects a broader shift toward treating autonomous agents as a new software supply-chain attack surface. As agents gain permission to write code, install tools, and operate across environments, dependency security and runtime isolation are becoming core enterprise requirements rather than optional add-ons.