INCIDENT MAP

Browse / Indirect Prompt Injection / CVE-2025-58764

Claude Code rg vulnerability does not protect against approval prompt bypass

CVE-2025-58764 ยท 2025-09-10 high

Class
Indirect Prompt Injection (filed by a model that read the advisory)
Technique
Code and command execution
Also involves
Tool and Agent Misuse
Affected
@anthropic-ai/claude-code (npm)
Gets past
Approval or confirmation prompt
CVSS
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
EPSS
0.5% chance of exploitation in 30 days

How it works, in short

Attacker-supplied text placed into the agent's context exploits a command-parsing flaw so an untrusted shell command runs without the confirmation prompt. (Our summary, written by a model. The source text is below.)

Details

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!

References

Source: GitHub Advisory Database, used under CC BY 4.0.