We use these services and cookies to improve your user experience. You may opt out if you wish, however, this may limit some features on this site.
Please see our statement on Data Privacy.
Claude Code is an agentic coding tool. In versions below 1.0.20, an error in command parsing makes it possible to bypass the Claude Code confirmation prompt to trigger execution of an untrusted command. Reliably exploiting this requires the ability to add untrusted content into a Claude Code context window. This is fixed in version 1.0.20.
Reserved 2025-07-29 | Published 2025-08-05 | Updated 2025-08-05 | Assigner GitHub_MCWE-78: Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')
github.com/...e-code/security/advisories/GHSA-x56v-x2h6-7j34
Support options