# Choosing the right tool safety approach for coding agents

DevFeed: [Choosing the right tool safety approach for coding agents](<https://devfeed.tech/articles/choosing-the-right-tool-safety-approach-for-coding-agents-33585.md>)

Original publisher: [Read original article](<https://blog.scottlogic.com/2026/07/15/choosing-the-right-tool-safety-approach-for-coding-agents.html>)

Author: Robat Williams

Published: 2026-07-15T12:00:00Z

Content type: article

Language: en

Sources: [Scott Logic](<https://devfeed.tech/sources/scott-logic.md>)

Topics: [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [developer tooling](<https://devfeed.tech/topics/developer-tooling.md>), [prompt injection](<https://devfeed.tech/topics/prompt-injection.md>), [AI Development](<https://devfeed.tech/topics/ai-development.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>)

Tags: [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [build](<https://devfeed.tech/tags/build.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [code](<https://devfeed.tech/tags/code.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [prompt-injection](<https://devfeed.tech/tags/prompt-injection.md>), [safety](<https://devfeed.tech/tags/safety.md>)

## AI overview

This article examines safety risks in coding agents, focusing on how models, runtimes such as Claude Code, and tools enable agents to act on their environment. It discusses permission-based harnesses, permission fatigue, prompt injection, and the limitations of relying solely on model alignment.

## Source excerpt

In coding agents, the trio of: models, runtimes (e.g. Claude Code), and tools (e.g. file write) are what makes agentic software development possible. While they work safely most of the time, the (unsafe) default setup many of us fall into does carry risk. In this post, I'll explore some things you could consider to make your own setup safer - or at least help you understand its limitations.