RCE via Command Parsing Bypass in Claude Code before 1.0.20
CVE-2025-54795 Published on August 5, 2025
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.
Weakness Type
What is a Shell injection Vulnerability?
The software constructs all or part of an OS command using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify the intended OS command when it is sent to a downstream component.
CVE-2025-54795 has been classified to as a Shell injection vulnerability or weakness.
Products Associated with CVE-2025-54795
You can be notified by email with stack.watch whenever vulnerabilities like CVE-2025-54795 are published in Anthropic Claude Code:
Affected Versions
anthropics claude-code Version < 1.0.20 is affected by CVE-2025-54795Exploit Probability
EPSS (Exploit Prediction Scoring System) scores estimate the probability that a vulnerability will be exploited in the wild within the next 30 days. The percentile shows you how this score compares to all other vulnerabilities.