Require approval before agents run shell commands
MaxKB AI agent flaw: injected content could run shell commands · Security incident · X · @DailyDarkWeb · Sep 2026
A CVSS 10 flaw was reported in the open-source MaxKB assistant, where untrusted chat or ingested content could trigger shell commands without human approval.
Lesson
Require human approval for any shell or code-execution tool and patch self-hosted AI platforms.
Fix prompt
Copy this into your own AI tool (Cursor, Lovable, Claude Code, Bolt…). It's general guidance written by us. Review what the AI suggests before applying it.
I use MaxKB, which can read web pages, files, emails or tool output. Help me reduce the risk of prompt injection (hidden instructions in content the AI reads). 1) List what my setup can access (files, terminal, browser, MCP servers, email, databases) and what it can do without asking me. 2) Point out the riskiest combinations, e.g. reading untrusted content while also having access to secrets or the ability to send data out. 3) Suggest concrete settings: require approval for commands and network calls, remove MCP servers I don't need, use read-only tokens, and keep the tool updated. 4) Give me a short checklist to follow before opening untrusted repos or documents. Don't change anything until I've approved your plan. Never ask me to paste API keys, passwords or .env contents; tell me where to check them myself.
Source: X ↗