← ClaudeAtlas

auditing-editor-extension-workspace-trustlisted

Audit an editor or IDE extension for actions it runs on untrusted workspace contents, after the workspace-trust capability and activation events are resolved. Covers a task, debug preLaunchTask, or command that auto-runs on folder open, a tool path or command template read from workspace settings and executed, a workspace-trust bypass where a risky operation runs in restricted mode, a language server that loads or executes a workspace-declared binary, repo-controlled data reaching a shell or task-execution sink, and an extension webview that renders repo content without a content-security policy. Use when reviewing an extension manifest (activation events, the untrusted-workspace capability), its workspace config handling, or its language-server tool resolution. A cloned untrusted repository is the source, an action the extension auto-runs on open is the sink, and repo-controlled code reaching execution without a trust gate is the bug.
UnboundCompute/security-agent-skills · ★ 27 · AI & Automation · score 80
Install: claude install-skill UnboundCompute/security-agent-skills
# Auditing editor extension workspace trust: what an untrusted repository makes the editor do on open An editor extension turns dangerous the moment merely opening a cloned repository makes it run code the repository controls. The threat is not a user choosing to run something; it is a drive-by, a hostile `.vscode/tasks.json`, a `settings.json` that names the compiler binary, an activation event that fires on folder open and shells out before the user has trusted anything. You audit it by resolving, per risky action, whether a workspace-trust gate or an explicit user gesture stands between the untrusted repo and the execution sink. The discipline is separating an action that genuinely fires on open from one that needs a deliberate click, and a value read from workspace settings from one read from user or global settings a repo cannot set. ## When to use - You are reviewing an editor or IDE extension manifest, its activation events, and its trust capability. - The extension reads workspace configuration, runs tasks, or resolves a tool or binary path from a repo. - You want to know whether opening a hostile repository executes code before the user trusts it. ## Scope check Audit only extensions you own or are authorized to assess, and open a crafted hostile workspace only on a machine and account in scope, an auto-executed task runs real code on your host. Adjudicate on the manifest and the handler. If you can't name the authorization, stop. ## The loop 1. **Resolve the