Blog
How AI agents get hijacked, what each attack looks like, and how to stop it. Written for developers and the people who run their machines.
-
Prompt injection in AI coding agents: what it is and how to stop it
Prompt injection hides instructions in files, issues and web pages that AI coding agents read. Here's how the attack works in Claude Code, Copilot and Cursor, and what actually stops it.
-
Can a GitHub Issue Hijack Your AI Coding Agent?
Yes. Any text a coding agent reads, including GitHub issues and tool output, can carry hidden instructions it treats as commands to run.
-
How to Stop AI Browser Extensions Leaking Company Data
AI agents built into Chrome, Edge and Brave can read whatever page they're on and act on it. Here's how to actually control that exposure.
