Agent security has two failure modes: miss the attack, or break the work.

A guardrail that blocks everything is safe. Can you stop dangerous tool calls without breaking legitimate work? We ran: But the number we care about most isn't detection alone. And very soon, we're open-sourcing the Agent Security Gateway itself. PS!
This is an AI-generated summary. ShortSingh links to the original source for the complete article.

Discussion (0)
Log in to join the discussion and vote.
Log in