[_flux]

In principle it could use e.g. the `gdb` and step until it gets the secret. Or it can know ahead where the app stores the cerentials.

We could use suid binaries (e.g. sudo) to prevent that, but currently I don't think we can. Most anyone would agree that using a separate process, for which the agent environment provides a connection, is a better solution.

[e12e]

Seperate process as a seperate os user, and/or namespace.

[_flux]

I mean definitely a good starting point is a share-nothing system, but then it becomes impossible to use tools (no shared filesystem, no networking), so everything needs to happen over connections the agent provides.

MCP looks like it would then fit that purpose, even if there was an MCP for providing access to a shell. Actually I think a shell MCP would be nice, because currently all agent environments have their own ways of permission management to the shell. At least with MCP one could bring the same shell permissions to every agent environment.

Though in practice I just use the shell, and not MCP almost at all; shell commands are much easier to combine, i.e. the agent can write and run a Python program that invokes any shell command. In the "MCP shell" scenario this complete thing would be handled by that one MCP, it wouldn't allow combining MCPs with each other.

Maybe an "agent shell" is what we need.

[e12e]

That is fine, but you give up any pretence of security - your agent can inspect your tool's process, environment variables etc - so can presumably leak API keys and other secrets.

Other comments have claimed that tools are/can be made "just as secure" - they can, but as the saying goes: "Security is not a convenience".