Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: Agent Vault – Open-source credential proxy and vault for agents

github.com

Post reply on HN
Print view View original

41–50 of 71 posts

Re: Show HN: Agent Vault – Open-source credential proxy and vault for agents

#41

Post by jimmypk »

10keane wrote: post #39

been thinking about this exact problem for a while. my own setup uses OS keyring with a token substitution pattern — the agent requests a credential by name, the substitution happens at execution time, the LLM never sees the raw value in context or logs. works reasonably well. but the problem with that model is it's static protection. if the agent process itself becomes hostile or gets prompt-injected, keyring doesn'…

[flagged]

Re: Show HN: Agent Vault – Open-source credential proxy and vault for agents

#43

Post by manojbajaj95 »

andreypk wrote: post #42

It looks promising if I have a request to llm with secrets is it handle it as well?

Try out, https://github.com/manojbajaj95/authsome . I'm trying to work with LLM secrets too. Still alpha, but thats the direction i'm taking

Re: Show HN: Agent Vault – Open-source credential proxy and vault for agents

#47

Post by hebetude »

It’s an idea that obfuscates keys a bit, but how are you going to prevent the agent from gaining access to the vault and keys itself? I’ve seen it reverse engineer many things to expose the underlying credentials. I can only think running this on a firewall that the agent can’t access to prevent escalation.

Re: Show HN: Agent Vault – Open-source credential proxy and vault for agents

#48

Post by mike-cardwell »

Does it work for websockets too, where the authentication is done in a websocket frame? Like for Home Assistant? Also, if the LLM manages to do something to reflect the authentication token back in a response, do you detect it and strip it out as an extra layer of protection?

Re: Show HN: Agent Vault – Open-source credential proxy and vault for agents

#50

Post by wfinigan »

Love this. Our team has been frustrated that nothing like this exists. You run into this problem as soon as you start thinking seriously about capable cloud agents, but there was no generic solution. Existing options are either tied to a specific cloud vendor or protocol, like git or MCP. We had a design on the whiteboard for something like this when this release dropped in our laps--with lots of thoughtful choices we hadn't gotten to yet. Thank you Tony and team.

Would the proxy as designed double as a domain-based allowlist, separate from the credential brokering?

Post reply on HN