# CVE-2025-59536: Claude Code's startup trust dialog could lead to Command Execution attack > Attackers can execute arbitrary code by tricking users into starting Claude Code in a malicious directory before accepting the trust dialog. - **Severity:** High 8.7 (`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`) - **Exploited in the wild:** Not known - **Login needed:** Not needed - **Attackable:** Over the internet - **Victim action needed:** A user has to click or open something - **Fix available:** Yes - **Published:** 3 Oct 2025 - **Updated:** 3 Oct 2025 - **Also known as:** GHSA-4fgq-fpq9-mr3g ## What is CVE-2025-59536? CVE-2025-59536 is a high-severity code injection vulnerability in anthropics claude-code, published on 3 Oct 2025. An attacker can exploit it over the internet without logging in, and only if a user opens a file or follows a link. ### Official 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. Weakness: CWE-94 (Improper Control of Generation of Code) ## Which versions are affected by CVE-2025-59536? 2 open source packages ship an affected version, including @anthropic-ai/claude-code. It affects 1 product. | Package | Ecosystem | Affected | Fixed in | | --- | --- | --- | --- | | `@anthropic-ai/claude-code` | npm | All versions | 1.0.111 | | `@anthropic-ai/claude-code` | npm | All versions | 1.0.111 | Products: Anthropic Claude Code. ## How do I fix CVE-2025-59536? Upgrade @anthropic-ai/claude-code to 1.0.111 or later. ## Is CVE-2025-59536 being exploited? There is no known exploitation of CVE-2025-59536 in the wild and no public exploit code. Public exploit code: - Working implementation: cryptographically verified short-lived identities for AI decision authentication — CVE-2025-59536 (Patent Pending US 64/006,746) (github_poc): https://github.com/AetherAI3/AETHER-PROTOCOL-P - 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. (github_poc): https://github.com/Rohitberiwala/Claude-Code-MCP-Injection-PoC - https://github.com/NetVanguard-cmd/CVE-2025-59536 (github_poc): https://github.com/NetVanguard-cmd/CVE-2025-59536 - 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 Backdoor patterns. (github_poc): https://github.com/TreRB/ai-ide-config-guard - Read-only safety scanner for Claude Code projects. Catches CVE-2025-59536, statusLine injection, prompt injection, and more. (github_poc): https://github.com/Razi-Interactive/claude-project-scanner - 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 untrusted repository. Static, zero-dep, local-first. (github_poc): https://github.com/Perufitlife/dotclaude-security ## Other vulnerabilities in anthropics claude-code - [CVE-2025-66032](https://insights.sbomify.com/CVE-2025-66032/): Claude Code Command Validation Bypass Allows Arbitrary Code Execution (high 8.7) - [CVE-2025-64755](https://insights.sbomify.com/CVE-2025-64755/): @anthropic-ai/claude-code has Sed Command Validation Bypass that Allows Arbitrary File Writes (high 8.7) - [CVE-2025-58764](https://insights.sbomify.com/CVE-2025-58764/): Claude Code rg command had Command Injection that allowed bypass of user approval prompt for command execution (high 8.7) - [CVE-2025-59041](https://insights.sbomify.com/CVE-2025-59041/): Claude Code vulnerable to arbitrary code execution caused by maliciously configured git email (high 8.7) - [CVE-2025-54795](https://insights.sbomify.com/CVE-2025-54795/): Claude Code echo command allowed bypass of user approval prompt for command execution (high 8.7) ## Fix prompt for AI coding agents ```text Check this codebase for CVE-2025-59536 and fix it if it is affected. What it is: CVE-2025-59536 is a high-severity code injection vulnerability in anthropics claude-code, published on 3 Oct 2025. An attacker can exploit it over the internet without logging in, and only if a user opens a file or follows a link. Exploitation: There is no known exploitation of CVE-2025-59536 in the wild and no public exploit code. Affected packages and fixed versions: - @anthropic-ai/claude-code (npm): affected all versions; fixed in 1.0.111 - @anthropic-ai/claude-code (npm): affected all versions; fixed in 1.0.111 Task: 1. Search the dependency manifests and lockfiles (for example package.json, package-lock.json, requirements.txt, poetry.lock, uv.lock, pom.xml, build.gradle, go.mod, Cargo.lock, Gemfile.lock) and any Dockerfiles for the affected packages, including transitive dependencies. 2. If an affected version is in use, upgrade it to the fixed version for its release line with the project's package manager, so the lockfile is regenerated. Prefer the smallest upgrade that fixes it. 3. If there is no fix, or the upgrade would break the build, do not guess: explain the risk and the safest workaround instead. 4. Run the tests and summarise what changed and why. 5. If nothing in the project is affected, say so and change nothing. Reference: https://insights.sbomify.com/CVE-2025-59536/ (Markdown: https://insights.sbomify.com/CVE-2025-59536/index.md) ``` ## Sources - CVE record: https://www.cve.org/CVERecord?id=CVE-2025-59536 - NVD: https://nvd.nist.gov/vuln/detail/CVE-2025-59536 - OSV: https://osv.dev/vulnerability/CVE-2025-59536 --- From sbomify Insights: https://insights.sbomify.com/CVE-2025-59536/ Summaries are generated and may contain mistakes; the official description above is the record.