UNIX Symbolic Link (Symlink) Following

Overview @anthropic-ai/claude-code is an Use Claude, Anthropic's AI assistant, right from your terminal. Claude can understand your codebase, edit files, run terminal commands, and handle entire workflows for you. Affected versions of this package are vulnerable to UNIX Symbolic Link Symlink...

Arbitrary Code Execution.

@anthropic-ai/claude-code is vulnerable to Arbitrary code execution. The vulnerability is due to improper parsing of shell commands involving $IFS and short CLI flags, which allows an attacker to bypass read-only validation and execute arbitrary code by injecting untrusted content into the contex...

Command Validation Bypass

@anthropic-ai/claude-code is vulnerable to command validation bypass. The vulnerability is due to improper validation of piped sed operations with the echo command, which allows an attacker to bypass file write restrictions and write to sensitive directories when the “accept edits” feature is...

Arbitrary Code Execution

@anthropic-ai/claude-code is vulnerable to Arbitrary Code Execution. The vulnerability is due to the automatic execution of Yarn plugins when running yarn --version, which allows an attacker to bypass the directory trust dialog and execute code before the user confirms trust in the directory...

GHSA-QXFV-FCPC-W36X Claude Code rg vulnerability does not protect against approval prompt bypass

Due to an error in command parsing, it was 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. Users on standard Claude Code auto-update will...

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...