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.
| Package (Ecosystem) | Introduced | Fixed | Limit |
|---|---|---|---|
| @anthropic-ai/claude-code(npm) | 0 | 1.0.20 | N/A |
CVSS Metrics
