Critical Cursor Flaws Could Let Prompt Injection Escape Sandbox and Run Commands

Cursor is a code editor built for programming with AI. Prior to 3.0, Cursor runs agent terminal commands in a sandbox by default, and the sandbox grants write access to the command's working directory. A flaw was identified in how the agent could modify the working_directory parameter, which could cause the sandbox to include writable paths outside the intended workspace. A malicious agent could set working_directory to a sensitive location and write arbitrary files outside the workspace under the user's privileges. This enables non-sandboxed Remote Code Execution — for example by overwriting the cursorsandbox helper so later commands run unsandboxed — with no user interaction beyond a benign prompt. This vulnerability is fixed in 3.0.

Cursor is a code editor built for programming with AI. Prior to 3.0, Cursor runs agent terminal commands in a sandbox by default. Before a Write, the agent canonicalizes the target path to confirm it stays inside the workspace, but when canonicalization fails it falls back to the original path and writes without approval. A malicious agent can create an in-workspace symlink that points outside the workspace and force canonicalization to fail — either because the target does not exist or because read permission is removed from the path — so the agent writes through the symlink to an arbitrary location without approval. A malicious agent could write arbitrary files outside the workspace under the user's privileges. This enables non-sandboxed Remote Code Execution — for example by overwriting the cursorsandbox helper so later commands run unsandboxed — with no user interaction beyond a benign prompt. This vulnerability is fixed in 3.0.