Summary
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 have received this fix automatically. Users performing manual updates are advised to update to the latest version.
Thank you to the NVIDIA AI Red Team for reporting this issue!
Impact
Untrusted input is evaluated as executable code within the application's runtime environment. Typical impact: arbitrary code execution within the application's privilege context.
Affected versions
Security releases
Kodem intelligence
Severity tells you how bad this could be in the worst case. It does not tell you whether you are exposed. Exploitability and impact are functions of runtime truth: whether the vulnerable code is present, reachable, and actually executes in your application. A vulnerable package can sit in your dependency tree and never run.
Kodem, an Intelligent Application Security platform, uses runtime intelligence to reveal which vulnerabilities actually execute in production, so teams prioritize the ones that genuinely matter. Kodem's runtime-powered SCA identifies whether this CVE is reachable in your applications.
Already deployed Kodem?
See it in your environmentNew to Kodem? Get a demo →Remediation advice
Kodem Kai can prioritize this vulnerability in your dependency tree and generate a fix recommendation.
Frequently Asked Questions
- What is CVE-2025-58764? CVE-2025-58764 is a high-severity code injection vulnerability in @anthropic-ai/claude-code (npm), affecting versions < 1.0.105. It is fixed in 1.0.105. Untrusted input is evaluated as executable code within the application's runtime environment.
- Which versions of @anthropic-ai/claude-code are affected by CVE-2025-58764? @anthropic-ai/claude-code (npm) versions < 1.0.105 is affected.
- Is there a fix for CVE-2025-58764? Yes. CVE-2025-58764 is fixed in 1.0.105. Upgrade to this version or later.
- Is CVE-2025-58764 exploitable, and should I be worried? Whether CVE-2025-58764 is exploitable in your environment depends on whether the vulnerable code is present and reachable. A CVSS score is a worst-case rating; it does not account for your specific deployment, configuration, or usage patterns. Kodem, an Intelligent Application Security platform, uses runtime intelligence to show which vulnerabilities actually execute in production, so you can focus on the ones that represent real risk. Get a demo
- What actually determines whether CVE-2025-58764 is exploitable, and how bad it is? Exploitability and impact are not fixed properties of a CVE. They depend on runtime truth: whether the vulnerable code is present, reachable, and actually executes in your application. A high CVSS score on a dependency that never runs is not the same as real risk. Kodem, an Intelligent Application Security platform, uses runtime intelligence to reveal which vulnerabilities actually execute in production, so teams prioritize the ones that genuinely matter.
- How do I fix CVE-2025-58764? Upgrade
@anthropic-ai/claude-codeto 1.0.105 or later.