Agent host
The program that runs the agent loop — the CLI, IDE extension or desktop app that assembles the context, sends it to the model, receives the tool calls and executes them. It matters for security because it is the only place that sees every step in order, and it is where enforcement hooks can exist at all. It is also why coverage claims must name a host: a control implemented as a hook in one host is not automatically present in another.
See also PreToolUse hook · action layer · detection vs prevention
Related terms
-
PreToolUse hook
Agents & architecture
A callback the agent host invokes after the model has requested a tool call but before the call executes, handing over the tool name and arguments and…
-
Action layer
Agents & architecture
The enforcement surface at the tool call, as opposed to the prompt layer, which tries to classify text before the model sees it.
-
Detection vs prevention
Testing & measurement
Detection notices something and produces a record; prevention stops it from happening. They are routinely conflated in agent-security claims, and the gap…
Agents & architecture
Where the attacks above actually land. The vocabulary here is worth precision, because the difference between "the model decided" and "the tool ran" is the difference between a risk and an incident.