←
Luke Hinds3,027 posts
Luke Hinds avatar

Luke Hinds

@decodebytes

CEO of @nolabshq - Creator of sigstore.dev , now building nono.sh - the agent security platform.

◷ Joined February 2021▧ 577 Photos and videos
Luke Hinds avatar
Luke Hinds@decodebytes·Nov 11

am I missing something here ? why not just render from the existing list and not have me trying to remember how they were named each time?

Post attachment
Luke Hinds avatar
Luke Hinds@decodebytes·Nov 1

Has anyone found a decent red team agent project around? OSS please, not interested vendor SaaS.

Luke Hinds avatar
Luke Hinds@decodebytes·Oct 19

AI agents don't just answer questions any more. They write code, run it, call tools, and spin up sub-agents to do the work. Every one of those hand-offs is a new place for things to go wrong: a leaked credential, a poisoned dependency, or a sub-agent that reads far more than it should. On 2 November I'm joining Amazon Web Services (AWS) for a webinar: Secure AI Agents on Amazon EKS: Sandboxing Sub-Agents with nono. We'll show how to layer two levels of defense: → Amazon EKS isolation around the workload → nono's kernel-enforced agent runtime protections around every agent and tool inside it No root, no code rewrites, nothing for the agent to talk its way around. If you're running agents on Kubernetes, or about to, come along. Registration link in the reply 👇 #AIAgents #Kubernetes #AmazonEKS #AppSec #OpenSource

Post attachment
Luke Hinds avatar
Luke Hinds@decodebytes·Oct 11

The Kubernetes (Official) agent-sandbox project now has a nice rendered example of building a zero trust Grafana agent on a nono protected pod - where the agent is limited to specific scoped execution path when using the Grafana LogCLI. Having this level of fine-grained execution means you can leave an agent unattended without concern of unwarranted actions as the credential is locked to only a single tools execution path. This is a deeper level of protection you won't get from other projects like @NVIDIA 's Open Agent Safety Platform, which although it can bind credentials to approved endpoints and restrict network access by binary, its sandbox policy does not constrain command-line arguments or make filesystem access and credentials specific to only an individual command and no other. agent-sandbox.sigs.k8s.io/do…

Pradipta Banerjee avatar
⟳ Luke Hinds retweeted
Pradipta Banerjee@pradipta_kr·Oct 2

It's been many months since I started using nono.sh for sandboxing my AI agents - claude/codex/opencode and with a few customisations to the default policy for my usage, it's working great. I have some use cases where I want the agent to create and work on rootless podman containers. For this, I switched to the podman remote option via the local unix socket. Local rootless podman within a nono sandbox didn't work for me. I "wrap" the agents using nono for my workflow because it integrates nicely with herdr, my default terminal when working with agents. Although AI agents are now coming with their own sandbox, somehow my trust in nono, as well as its portability across my different OS environments, made it my de facto choice. Great work on nono.sh from @decodebytes and team.

Luke Hinds avatar
Luke Hinds@decodebytes·Sep 21

Something we have been experimenting with using nono's remote capable multiplexer

1:00
Luke Hinds avatar
Luke Hinds@decodebytes·Sep 17

Running a headless pi agent from 10,000 feet, started remotely with a full TUI from my terminal in London, to then connect via our web portal to check on progress during flight to then use my terminal again later to connect in Amsterdam , fully secured in Nono.sh - no more walking around with a lid open. Pm me to learn more or find me at #AGNTCon

Post attachment
TechInformed avatar
⟳ Luke Hinds retweeted
TechInformed@TechInformed·Sep 8

#Firewalls were built to keep attackers out. But what happens when #AIagents can already operate inside your systems? We had coffee with @decodebytes , cofounder of nolabs.ai, to explore the new security challenge. Read more: techinformed.com/the-securit…