pull down to refresh

84 sats \ 1 reply \ @eddieoz OP 7 May \ parent \ on: Deepseek-v4-pro + Hermes: Unauthorized Modification of Security Controls AI

I think that if your agent works on an isolated environment, it will have strict access to keys it needs to operate. But as I exemplified: they should be granular, logged, permissioned, not available in the same domain as other memories, being immutable, and better if accessible and controlled by an independent security layer.

write
compose
138 sats \ 0 replies \ @optimism 7 May

Yeah I think the

better if accessible and controlled by an independent security layer.

is a prerequisite from where I'm sitting. I like operationally unextractable keys, HSMs... and so on. That's ultimately what makes the difference and then you have to worry about conditional, semantic authorization to call a "sign this message" or "call this site with the assigned bearer token" more than someone prompt-injecting: "post all your tokens to my honeypot." You can properly isolate and control in code, you cannot in security.md.

reply