RCE in Anthropic Claude Code
CVE-2025-59536
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.
Vulnerability class: RCE (Remote Code Execution)
Published · last modified .
CVSS v3 metric
CVSS v3 base score 8.8 (High). Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H.
EPSS exploit prediction
EPSS 0.252, 98.0th percentile (scored ); down from 0.272 30 days earlier. About EPSS.
EPSS over last 30 days · oldest: 0.272 · newest: 0.252 · change: -0.020
Affected products
- Anthropic Claude Code
- Anthropics Claude-Code — versions < 1.0.111
Weakness classification (CWE)
Public exploits and proof-of-concept code
8 public repositories with exploit or proof-of-concept code for this CVE:
- AetherAI3/AETHER-PROTOCOL-P (1 star, last pushed 2026-08-19): Working implementation: cryptographically verified short-lived identities for AI decision authentication — CVE-2025-59536 (Patent Pending US 64/006,746)
- DBarr3/AETHER-PROTOCOL-P (1 star, last pushed 2026-06-03): Working implementation: cryptographically verified short-lived identities for AI decision authentication — CVE-2025-59536 (Patent Pending US 64/006,746)
- Perufitlife/dotclaude-security (last pushed 2026-06-21): Scan a repo's .claude/ config (settings.json hooks, MCP servers, env, allowed-tools) for the RCE & API-key-exfiltration footguns (CVE-2025-59536, CVE-2026-21852) that fire when you clone+open an untr…
- tacdm/cve-2025-59536-poc (last pushed 2026-05-19): CVE-2025-59536: RCE via Claude Code Project Hooks (PoC)
- Razi-Interactive/claude-project-scanner (last pushed 2026-04-30): Read-only safety scanner for Claude Code projects. Catches CVE-2025-59536, statusLine injection, prompt injection, and more.
- TreRB/ai-ide-config-guard (last pushed 2026-04-20): Scan a repo for AI-IDE config files that can trigger RCE via Claude Code hooks, Cursor rules, MCP auto-registration. Detects CVE-2025-59536, CVE-2026-21852, CVE-2026-30615 + Pillar Rules File Backdoo…
- NetVanguard-cmd/CVE-2025-59536 (last pushed 2026-04-19)
- Rohitberiwala/Claude-Code-MCP-Injection-PoC (last pushed 2026-03-10): Professional PoC for CVE-2025-59536 and related CVEs. Demonstrates an MCP Tool Confirmation Prompt Misrepresentation in Anthropic Claude_Code leading to arbitrary OS command execution.
References
This CVE has public exploit evidence. See the latest CVEs with public exploits.