CVE-2025-54795: Claude Code echo command allowed bypass of user approval prompt for command execution

Severity: critical (CVSS 9.8 v3.1)
Exploited in the wild: not listed in CISA KEV
EPSS: 1.0% probability of exploitation in the next 30 days
Public exploit or detection template: none known
Published: 2025-08-05 · updated 2026-06-17
Weakness: CWE-78

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 products

anthropics claude-code: before 1.0.20 — fixed in 1.0.20

How to fix

Upgrade to a fixed version: anthropics claude-code 1.0.20. Check the vendor advisory for mitigations.

References

https://github.com/anthropics/claude-code/security/advisories/GHSA-x56v-x2h6-7j34

Get alerted when CVE-2025-54795 or the next vulnerability affects your stack