https://cve.radiocsirt.org Contains only the most 10 recent entries. http://www.rssboard.org/rss-specification python-feedgen en Tue, 06 Oct 2026 09:44:38 +0000 https://cve.radiocsirt.org/vuln/euvd-2026-276634 EUVD-2026-276634 https://cve.radiocsirt.org/vuln/euvd-2026-276634 https://cve.radiocsirt.org/vuln/fkie_cve-2026-33068 <p>Claude Code is an agentic coding tool. Versions prior to 2.1.53 resolved the permission mode from settings files, including the repo-controlled .claude/settings.json, before determining whether to display the workspace trust confirmation dialog. A malicious repository could set permissions.defaultMode to bypassPermissions in its committed .claude/settings.json, causing the trust dialog to be silently skipped on first open. This allowed a user to be placed into a permissive mode without seeing the trust confirmation prompt, making it easier for an attacker-controlled repository to gain tool execution without explicit user consent. This issue has been patched in version 2.1.53.</p> <p>Claude Code is an agentic coding tool. Versions prior to 2.1.53 resolved the permission mode from settings files, including the repo-controlled .claude/settings.json, before determining whether to display the workspace trust confirmation dialog. A malicious repository could set permissions.defaultMode to bypassPermissions in its committed .claude/settings.json, causing the trust dialog to be silently skipped on first open. This allowed a user to be placed into a permissive mode without seeing the trust confirmation prompt, making it easier for an attacker-controlled repository to gain tool execution without explicit user consent. This issue has been patched in version 2.1.53.</p> https://cve.radiocsirt.org/vuln/fkie_cve-2026-33068 https://cve.radiocsirt.org/vuln/ghsa-mmgp-wc2j-qcv7 <p><strong>Affected:</strong> npm: @anthropic-ai/claude-code</p> <p>Claude Code resolved the permission mode from settings files, including the repo-controlled `.claude/settings.json`, before determining whether to display the workspace trust confirmation dialog. A malicious repository could set `permissions.defaultMode` to `bypassPermissions` in its committed `.claude/settings.json`, causing the trust dialog to be silently skipped on first open. This allowed a user to be placed into a permissive mode without seeing the trust confirmation prompt, making it easier for an attacker-controlled repository to gain tool execution without explicit user consent.</p> <p>Users on standard Claude Code auto-update have received this fix already. Users performing manual updates are advised to update to the latest version.</p> <p>Thank you to hackerone.com/cantina_xyz for reporting this issue.</p> <p><strong>Affected:</strong> npm: @anthropic-ai/claude-code</p> <p>Claude Code resolved the permission mode from settings files, including the repo-controlled `.claude/settings.json`, before determining whether to display the workspace trust confirmation dialog. A malicious repository could set `permissions.defaultMode` to `bypassPermissions` in its committed `.claude/settings.json`, causing the trust dialog to be silently skipped on first open. This allowed a user to be placed into a permissive mode without seeing the trust confirmation prompt, making it easier for an attacker-controlled repository to gain tool execution without explicit user consent.</p> <p>Users on standard Claude Code auto-update have received this fix already. Users performing manual updates are advised to update to the latest version.</p> <p>Thank you to hackerone.com/cantina_xyz for reporting this issue.</p> https://cve.radiocsirt.org/vuln/ghsa-mmgp-wc2j-qcv7