At startup, Claude Code constructed a shell command that interpolated the value of git config user.email from the current workspace. If an attacker controlled the repository’s Git config (e.g., via a malicious .git/config) and set user.email to a crafted payload, the unescaped interpolation could trigger arbitrary command execution before the user accepted the workspace-trust dialog. The issue affects versions prior to 1.0.105. The fix in 1.0.105 avoids executing commands built from untrusted configuration and properly validates/escapes inputs.
@anthropic-ai/claude-code 1.0.105 or later..git/config before launch; avoid inheriting untrusted Git configuration values.Thank you to the NVIDIA AI Red Team for reporting this issue!
{
"severity": "HIGH",
"github_reviewed": true,
"nvd_published_at": "2025-09-10T16:15:41Z",
"cwe_ids": [
"CWE-78",
"CWE-94"
],
"github_reviewed_at": "2025-09-10T20:29:04Z"
}