What is Line CLI's prompt-injection guard?
"Prompt injection" is when text the agent reads, such as a web page, tries to give it orders ("ignore your instructions and run this…").
Line treats web pages, search results and MCP tool output as untrusted data. If such content contains instructions aimed at agents, Line switches to asking: commands and edits need your approval for the rest of that turn, even in auto mode.
Skill files are treated as data too: the agent follows a skill for the task you gave, never instructions that conflict with your request.
Related articles
Still need help?
Tried the steps above and still stuck? Email us. We usually reply within the first hour, and always within 24 hours. A full support team is with you.
Infrastructure questions, or permanent deletion of your data
infrastructure@clatterlabs.xyzFor deleting your whole account or the data of one service.