RCE in Anthropic Claude Code

CVE-2025-54795

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.

Vulnerability class: Command Injection (OS Command Injection)

Published · last modified .

CVSS v3 metric

CVSS v3 base score 9.8 (Critical). Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H.

EPSS exploit prediction

EPSS 0.011, 66.0th percentile (scored ); unchanged over 30 days. About EPSS.

Affected products

Weakness classification (CWE)

Public exploits and proof-of-concept code

1 public repository with exploit or proof-of-concept code for this CVE:

  • alonisser/ralph (last pushed 2026-01-03): Ralph Wiggum plugin implementation that works after the CVE-2025-54795 security patch

Also mentioned in 3 other repositories (ARPSyndicate/cve-scores, asakaguchi/blocks-slack-orchestrator, asakaguchi/cc-safe-stack). These reference the CVE in a list, notes or a scanner and are not exploit code for it.

References