@reach_vb: PSA: if you care about your data and infrastructure then please *don’t* run your coding agent in yolo mode To secure yo…
Summary
A PSA advises developers to avoid running coding agents in 'yolo mode' to prevent destructive actions like accidental file deletion, recommending approval workflows, safety rules, and pre-tool hooks.
View Cached Full Text
Cached at: 07/11/26, 09:25 AM
PSA: if you care about your data and infrastructure then please don’t run your coding agent in yolo mode
To secure your workspace I recommend the following:
-
Use “Approve for me” - you can have codex review what it’ll run with a sub agent to make sure that it’s not destructive!
-
Use Rules - you can set up a rule for codes to never run destructive commands like “rm - rf”, this needs to be in a .rules file and you can ask codex to create it too
-
Setup a PreToolUse Hook - you can ask codex to set this up for you as well
Matt Shumer (@mattshumer_): GPT-5.6-Sol just accidentally deleted almost ALL of my Mac’s files.
And this is why I trust Fable 1000x more.
Similar Articles
@akshay_pachaar: https://x.com/akshay_pachaar/status/2067646389291725258
AI coding agents like Claude Code can be dangerous because they generate code without considering authorization and operational safety, potentially leading to unauthorized writes like deleting production databases. The real risk is not the code quality but the lack of runtime access controls.
@houjun_liu: Your coding agent may be secretly sticking vulnerabilities into your code!! Wouldn't you want to fix that? Hint: asking…
The article highlights a critical issue where AI coding agents may introduce security vulnerabilities into code, noting that simply asking for secure code is insufficient to prevent this.
AI coding agents need a local safety boundary before they touch files or run commands
Discussion on the need for local safety boundaries in AI coding agents to prevent unauthorized file access or command execution.
@omarsar0: As we target more complex use of coding agents (e.g., dynamic workflows and /goals) on long-horizon tasks, you will sta…
Discusses challenges with coding agents in complex long-horizon tasks, highlighting bizarre user experience issues and inefficient agent interactions, and advocates for more control over the agent harness.
How do you stop coding agents from touching production data?
Discusses strategies to prevent AI coding agents from accidentally modifying production databases, advocating for read-only access, sandboxed environments, and approval gates over relying solely on prompts.