Ask HN: How do you give AI agents access without over-permissioning?
6 points by NBenkovich 2 days ago | 14 comments
- ninan980805 1 day agoI am surprised vercel doesn't have fine-grained control. Supabase for example allows developer to config IAM roles and which role has read-only or read-write access to which tables. And each IAM role comes with its own token. This way people can easily configure a set of permissions agent should have access to and give that token to agent.
- verdverm 2 days agoIf you use a cloud like AWS, GCP, or Azure... you give it an SA and you give access with very fine grained permission controls
It's more about specific apps than modern apps and how your org puts their infra together.
I don't have your problem, I can give my agents all sorts of environments with a spectrum of access vs restrictions
[-]- NBenkovich 2 days agoAgreed on cloud IAM. AWS, GCP, and Azure handle fine-grained access well.
The problem is higher-level platforms and SaaS. Once agents need feedback from deployment, CI, logs, or config tools, permissions often collapse into “full token or nothing”. Vercel is just one example.
That’s the gap I’m pointing at.
[-]- verdverm 2 days agoMaybe the problem is your SaaS choices
I don't have problems with permissions in any of those things you listed. Do mainly k8s based infra
[-]- vitramir 1 day agoterraform cloud, argocd, vercel and supabase (modern stack for micro apps), sentry (doesn't have per project permissions), sendgrid, etc...
What does your stack look like beyond Kubernetes and AWS? It’s hard to imagine everything there supports truly fine-grained permissions.
[-]- verdverm 1 day agoActually, almost everything stays within the private cloud, health care industry
GCP (main), AWS/Azure (b/c customers), Jenkins/Argo
TF/Helm are IaC and run from containers, no hashicorp services
CloudSQL, why are you sending your db queries to a SaaS?
LGTM for observability
The vendors we do have are WIF'd (i.e. code & secops scanning)
WIF is the key, mature vendors are supporting WIF, and amazingly the hyperscalers are supporting each others WIFs for cross-cloud, so we can give a GCP SA, AWS perms and vice versa
- vitramir 2 days agoThere’s also a related issue: many services use per-project API tokens. When agents need access to multiple projects, you have to pass several tokens at once. Which often leads to confusion and erratic behavior, including severe hallucinations.[-]
- NBenkovich 2 days agoYeah, totally. Per-project tokens make it worse. Once you hand an agent multiple tokens, there’s no clean way to say “use this one vs that one”.
- imidov 2 days agoThere’s no clean read-only or capability-scoped access.-> always found that to be a no brainer backend feature, somehow most platforms misses that[-]
- NBenkovich 2 days agoYeah, agreed. Read-only and capability-scoped access feels like a no-brainer.
Most platforms were built assuming a human behind the UI. Once you introduce AI agents, the missing permission layers start to show.
- fsflover 2 days agoQubes OS allows to isolate any workflow with hardware-assisted virtualization.[-]
- NBenkovich 2 days agoHow can it help? Could you share more details please?[-]
- fsflover 2 days agoOn Qubes, all software runs in virtual machines, isolated with strong virtualization. Anything you do in one dedicated VM has no effect on all others, so any unrelated data will not be accessible by the AI agents.[-]
- NBenkovich 2 days agoIt’s great but how can it help with agent’s permissions for cloud services without fine grained tokens?