Redacted warning
Cursor was stopped before following a hidden instruction
A redacted example of a prompt injection via a file comment.
What tried to happen: Cursor attempted to run a shell command after reading a hidden instruction in a file.
Why risky: The instruction was embedded in an HTML comment invisible to the developer.
What Guard did: HOL Guard paused the command and showed the source of the instruction.
Safe next step
Review file contents that contain HTML comments or zero-width characters before letting agents act.