https://cve.radiocsirt.org/rss/recent/all/10 Most recent entries from all 2026-10-17T05:47:59.808684+00:00 Vulnerability-Lookup csirt@opendfir.org python-feedgen Contains only the most 10 recent entries. https://cve.radiocsirt.org/vuln/euvd-2026-252514 EUVD-2026-252514 2026-10-17T05:47:59.812061+00:00 EUVD-2026-252514 https://cve.radiocsirt.org/vuln/fkie_cve-2025-58764 fkie_cve-2025-58764 2026-10-17T05:47:59.812094+00:00

Claude Code is an agentic coding tool. Due to an error in command parsing, versions prior to 1.0.105 were vulnerable to a bypass of 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 version 1.0.105 or the latest version.

 https://cve.radiocsirt.org/vuln/ghsa-qxfv-fcpc-w36x GHSA-qxfv-fcpc-w36x — Claude Code rg vulnerability does not protect against approval prompt bypass 2026-10-17T05:47:59.812127+00:00

Affected: npm: @anthropic-ai/claude-code

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!