Vulnerability · Published Aug 5, 2025 · Assigned by GitHub_M
CVE-2025-54795Claude Code echo command allowed bypass of user approval prompt for command execution
High 8.7
In plain English
A high-severity OS command injection in claude-code from anthropics. There are no confirmed reports of exploitation so far. The chance it is exploited in the next 30 days is estimated at 1.1% (higher than 66% of all known vulnerabilities). Ready-made attack tooling exists: public proof-of-concept code. Fixed versions are available - upgrade the affected package.
Official description
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.
Affected packages & fixed versions
| Ecosystem | Package | Fixed in | Advisory |
|---|---|---|---|
| npm | @anthropic-ai/claude-code | 1.0.20 | GHSA-x56v-x2h6-7j34 |
Affected products (as reported)
| Vendor | Product | Versions |
|---|---|---|
| anthropics | claude-code | < 1.0.20 |
Weakness: CWE-78 · Vector: CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N