Your AI Coding Tools Have an Invisible Attack Surface. One Model Falls for It Every Time.

Researchers find 63 MCP servers with hidden Unicode characters in tool descriptions, and GPT-5.4 follows the invisible instructions with 100% compliance.

Read More

GlassWorm Is Hiding Malware in Invisible Code and Pushing It Into Your Python Repos

GlassWorm steals GitHub tokens, then injects malicious code written in invisible Unicode characters into repos developers already trust. 151 packages hit in one week.

Read More