I’m looking to run OpenClaw on my homelab. Has anyone successfully got it running with Docker? I followed the Docker instructions on their website, got Ollama running with a lightweight model, but couldn’t get the openclaw dashboard working.
I was hoping to have it everyday, look through the hundreds of job alert emails I get, and output a list of jobs for me to apply for. It’ll compare my resume to the listing, check the age of the listing, etc.
I know it’s highly susceptible to prompt injection, but if I have it in a container, with a email made specifically for OpenClaw I’m hoping it will be relatively safe?
Simple put, no. In order to be save with a LLM that can execute stuff on its own it needs to be completely sandboxed.
A very nice talk about flaws in agentic AI can be found here: https://media.ccc.de/v/39c3-agentic-probllms-exploiting-ai-computer-use-and-coding-agents