chrome thorn
Security audit
Summary: 2 critical · 7 warn · 1 info
CRITICAL Small models require sandboxing and web tools disabled
Small models (<=300B params) detected: - ollama/medgemma:27b (27B) @ agents.defaults.model.primary (unsafe; sandbox=off; web=[off]) No web/browser tools detect…
Fix: If you must use small models, enable sandboxing for all sessions (agents.defaults.sandbox.mode="all") and disable web_search/web_fetch/browser (tools.deny=["group:web","browser"]).
I am running Ollama models in OpenClaw, but after configuration, it is able to send two or three messages in a chat, then it stops completely. When I run OpenClaw status, it shows this security audit. Any help?