{"id":"CVE-2025-59536","aliases":["EUVD-2025-32507","GHSA-4fgq-fpq9-mr3g"],"status":"published","title":"Claude Code's startup trust dialog could lead to  Command Execution attack","description":"Claude Code is an agentic coding tool. Versions before 1.0.111 were vulnerable to Code Injection due to a bug in the startup trust dialog implementation. Claude Code could be tricked to execute code contained in a project before the user accepted the startup trust dialog. Exploiting this requires a user to start Claude Code in an untrusted directory. 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. This issue is fixed in version 1.0.111.","severity":{"version":"4.0","score":8.7,"vector":"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","level":"high","assessor":"cna","from":"cve"},"epss":{"day":"2026-11-10","score":0.24887,"percentile":0.97927,"model":"v2026.06.15"},"facts":{"in_kev":false,"known_exploited":false,"public_exploit":true,"fix_available":true},"cwes":["CWE-94"],"published":"2025-10-03T06:34:48Z","modified":"2026-10-12T15:10:00Z","exploits":[{"source":"pocgithub","id":"AetherAI3/AETHER-PROTOCOL-P","title":"AetherAI3/AETHER-PROTOCOL-P","date":"2026-03-16","url":"https://github.com/AetherAI3/AETHER-PROTOCOL-P"},{"source":"pocgithub","id":"NetVanguard-cmd/CVE-2025-59536","title":"NetVanguard-cmd/CVE-2025-59536","date":"2026-04-19","url":"https://github.com/NetVanguard-cmd/CVE-2025-59536"},{"source":"pocgithub","id":"Perufitlife/dotclaude-security","title":"Perufitlife/dotclaude-security","date":"2026-06-21","url":"https://github.com/Perufitlife/dotclaude-security"},{"source":"pocgithub","id":"Razi-Interactive/claude-project-scanner","title":"Razi-Interactive/claude-project-scanner","date":"2026-04-30","url":"https://github.com/Razi-Interactive/claude-project-scanner"},{"source":"pocgithub","id":"Rohitberiwala/Claude-Code-MCP-Injection-PoC","title":"Rohitberiwala/Claude-Code-MCP-Injection-PoC","date":"2026-03-10","url":"https://github.com/Rohitberiwala/Claude-Code-MCP-Injection-PoC"},{"source":"pocgithub","id":"TreRB/ai-ide-config-guard","title":"TreRB/ai-ide-config-guard","date":"2026-04-20","url":"https://github.com/TreRB/ai-ide-config-guard"}],"fixes":[{"ecosystem":"npm","package":"@anthropic-ai/claude-code","fixed_in":["1.0.111"],"sources":["ghsa","osv"]}],"affected":[{"source":"ghsa","ecosystem":"npm","package":"@anthropic-ai/claude-code","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"1.0.111"}]}]},{"source":"osv","ecosystem":"npm","package":"@anthropic-ai/claude-code","ranges":[{"type":"SEMVER","events":[{"introduced":"0"},{"fixed":"1.0.111"}]}]}],"products":[{"vendor":"anthropic","product":"claude_code"},{"vendor":"anthropics","product":"claude-code"}],"references":[{"url":"https://github.com/anthropics/claude-code/security/advisories/GHSA-4fgq-fpq9-mr3g","tags":["x_refsource_CONFIRM","Vendor Advisory","web"]},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2025-59536","tags":["advisory"]},{"url":"https://github.com/advisories/GHSA-4fgq-fpq9-mr3g"},{"url":"https://github.com/anthropics/claude-code","tags":["package"]}],"sources":{"cve":[{"id":"CVE-2025-59536","title":"Claude Code's startup trust dialog could lead to  Command Execution attack","description":"Claude Code is an agentic coding tool. Versions before 1.0.111 were vulnerable to Code Injection due to a bug in the startup trust dialog implementation. Claude Code could be tricked to execute code contained in a project before the user accepted the startup trust dialog. Exploiting this requires a user to start Claude Code in an untrusted directory. 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. This issue is fixed in version 1.0.111.","status":"published","published":"2025-10-03T06:34:48.398Z","modified":"2025-10-03T13:26:23.309Z","cvss":[{"version":"4.0","score":8.7,"vector":"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","level":"high","assessor":"cna"}],"cwes":["CWE-94"],"updated_at":"2026-11-02T14:32:47.812946Z"}],"euvd":[{"id":"EUVD-2025-32507","description":"Claude Code is an agentic coding tool. Versions before 1.0.111 were vulnerable to Code Injection due to a bug in the startup trust dialog implementation. Claude Code could be tricked to execute code contained in a project before the user accepted the startup trust dialog. Exploiting this requires a user to start Claude Code in an untrusted directory. 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. This issue is fixed in version 1.0.111.","status":"published","published":"2025-10-03T06:34:48Z","modified":"2025-10-03T13:26:23Z","cvss":[{"version":"4.0","score":8.7,"vector":"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","level":"high"}],"updated_at":"2026-11-02T20:31:36.727084Z"}],"ghsa":[{"id":"GHSA-4fgq-fpq9-mr3g","title":"Claude Code can execute commands prior to the startup trust dialog ","description":"Due to a bug in the startup trust dialog implementation, Claude Code could be tricked to execute code contained in a project before the user accepted the startup trust dialog. Exploiting this requires a user to start Claude Code in an untrusted directory. \n\nUsers on standard Claude Code auto-update will have received this fix automatically. Users performing manual updates are advised to update to the latest version.\n\nThank you to https://hackerone.com/avivdon for reporting this issue!","status":"published","published":"2025-10-03T14:16:34Z","modified":"2025-10-03T14:16:36Z","cvss":[{"version":"4.0","score":8.7,"vector":"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","level":"high"}],"cwes":["CWE-94"],"updated_at":"2026-11-02T14:38:59.83883Z"}],"nvd":[{"id":"CVE-2025-59536","description":"Claude Code is an agentic coding tool. Versions before 1.0.111 were vulnerable to Code Injection due to a bug in the startup trust dialog implementation. Claude Code could be tricked to execute code contained in a project before the user accepted the startup trust dialog. Exploiting this requires a user to start Claude Code in an untrusted directory. 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. This issue is fixed in version 1.0.111.","status":"published","published":"2025-10-03T07:15:44.55Z","modified":"2026-10-12T15:10:00.207Z","cvss":[{"version":"4.0","score":8.7,"vector":"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/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X","level":"high","assessor":"secondary"},{"version":"3.1","score":8.8,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H","level":"high","assessor":"primary"}],"cwes":["CWE-94"],"updated_at":"2026-11-02T14:11:34.090044Z"}],"osv":[{"id":"GHSA-4fgq-fpq9-mr3g","title":"Claude Code can execute commands prior to the startup trust dialog ","description":"Due to a bug in the startup trust dialog implementation, Claude Code could be tricked to execute code contained in a project before the user accepted the startup trust dialog. Exploiting this requires a user to start Claude Code in an untrusted directory. \n\nUsers on standard Claude Code auto-update will have received this fix automatically. Users performing manual updates are advised to update to the latest version.\n\nThank you to https://hackerone.com/avivdon for reporting this issue!","status":"published","published":"2025-10-03T14:16:34Z","modified":"2025-10-03T14:57:25.457969Z","cvss":[{"version":"4.0","score":8.7,"vector":"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","level":"high"}],"cwes":["CWE-94"],"updated_at":"2026-11-02T15:46:36.782754Z"}]}}