{"answers":{"affected":"2 open source packages ship an affected version, including @anthropic-ai/claude-code. It affects 1 product.","exploited":"There is no known exploitation of CVE-2025-59536 in the wild and no public exploit code.","fix":"Upgrade @anthropic-ai/claude-code to 1.0.111 or later.","what":"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."},"fix_prompt":"Check this codebase for CVE-2025-59536 and fix it if it is affected.\n\nWhat 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.\nExploitation: There is no known exploitation of CVE-2025-59536 in the wild and no public exploit code.\n\nAffected packages and fixed versions:\n- @anthropic-ai/claude-code (npm): affected all versions; fixed in 1.0.111\n- @anthropic-ai/claude-code (npm): affected all versions; fixed in 1.0.111\n\nTask:\n1. 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.\n2. 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.\n3. If there is no fix, or the upgrade would break the build, do not guess: explain the risk and the safest workaround instead.\n4. Run the tests and summarise what changed and why.\n5. If nothing in the project is affected, say so and change nothing.\n\nReference: https://insights.sbomify.com/CVE-2025-59536/ (Markdown: https://insights.sbomify.com/CVE-2025-59536/index.md)","id":"CVE-2025-59536","markdown":"https://insights.sbomify.com/CVE-2025-59536/index.md","name":"CVE-2025-59536","record":{"aliases":["GHSA-4fgq-fpq9-mr3g"],"analysis":{"component_type":"developer_tool","fix_type":"upgrade","impacts":["code_execution"],"network_reachable":"yes","non_default_config":false,"product_category":"Claude Code CLI","requires_auth":"none","summary":"Attackers can execute arbitrary code by tricking users into starting Claude Code in a malicious directory before accepting the trust dialog.","user_interaction":"required","vuln_class":"code_injection"},"analysis_generated_by":"qwen3.8-flash-next","assigner":"GitHub_M","cpe":[{"product":"claude_code","vendor":"anthropic"}],"cvss":{"score":8.7,"severity":"high","source":"cna","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","version":"4.0"},"cwes":[{"id":"CWE-94","name":"Improper Control of Generation of Code"}],"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.","ecosystems":["npm"],"exploits":{"exploitdb":0,"first_seen":"2026-03-10","github_poc":6,"max_poc_stars":1,"metasploit":0,"nuclei":0,"refs":[{"date":"2026-03-16T19:43:41Z","kind":"github_poc","ref":"https://github.com/AetherAI3/AETHER-PROTOCOL-P","stars":1,"title":"Working implementation: cryptographically verified short-lived identities for AI decision authentication — CVE-2025-59536 (Patent Pending US 64/006,746)"},{"date":"2026-03-10T05:04:03Z","kind":"github_poc","ref":"https://github.com/Rohitberiwala/Claude-Code-MCP-Injection-PoC","stars":0,"title":"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."},{"date":"2026-04-19T06:22:28Z","kind":"github_poc","ref":"https://github.com/NetVanguard-cmd/CVE-2025-59536","stars":0,"title":null},{"date":"2026-04-20T06:41:02Z","kind":"github_poc","ref":"https://github.com/TreRB/ai-ide-config-guard","stars":0,"title":"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."},{"date":"2026-04-30T04:16:55Z","kind":"github_poc","ref":"https://github.com/Razi-Interactive/claude-project-scanner","stars":0,"title":"Read-only safety scanner for Claude Code projects. Catches CVE-2025-59536, statusLine injection, prompt injection, and more."},{"date":"2026-06-21T11:50:53Z","kind":"github_poc","ref":"https://github.com/Perufitlife/dotclaude-security","stars":0,"title":"Scan a repo's .claude/ config (settings.json hooks, MCP servers, env, allowed-tools) for the RCE \u0026 API-key-exfiltration footguns (CVE-2025-59536, CVE-2026-21852) that fire when you clone+open an untrusted repository. Static, zero-dep, local-first."}],"tier":"poc_unverified"},"has_fix":true,"headline":"Claude Code's startup trust dialog could lead to Command Execution attack","id":"CVE-2025-59536","indexable":true,"kev":null,"kind":"cve","links":{"ecosystem":"npm","product":null,"products":[],"type":"code_injection","year":"2025"},"n_packages":2,"n_references":1,"next":{"headline":"argo-cd is vulnerable to unauthenticated DoS attack via malformed Gogs webhook payload","id":"CVE-2025-59537"},"packages":[{"ecosystem":"npm","fixed":["1.0.111"],"introduced":["0"],"last_affected":[],"package":"@anthropic-ai/claude-code","purl":null,"source":"GHSA-4fgq-fpq9-mr3g"},{"ecosystem":"npm","fixed":["1.0.111"],"introduced":["0"],"last_affected":[],"package":"@anthropic-ai/claude-code","purl":"pkg:npm/%40anthropic-ai/claude-code","source":"GHSA-4fgq-fpq9-mr3g"}],"prev":{"headline":"DotNetNuke.Core allows loading of unused themes on anonymous clients through query parameters","id":"CVE-2025-59535"},"products":["claude-code"],"published":"2025-10-03","related":[{"cvss_score":8.7,"headline":"Claude Code Command Validation Bypass Allows Arbitrary Code Execution","id":"CVE-2025-66032","kev_date_added":null,"published":"2025-12-03"},{"cvss_score":8.7,"headline":"@anthropic-ai/claude-code has Sed Command Validation Bypass that Allows Arbitrary File Writes","id":"CVE-2025-64755","kev_date_added":null,"published":"2025-11-21"},{"cvss_score":8.7,"headline":"Claude Code rg command had Command Injection that allowed bypass of user approval prompt for command execution","id":"CVE-2025-58764","kev_date_added":null,"published":"2025-09-10"},{"cvss_score":8.7,"headline":"Claude Code vulnerable to arbitrary code execution caused by maliciously configured git email","id":"CVE-2025-59041","kev_date_added":null,"published":"2025-09-10"},{"cvss_score":8.7,"headline":"Claude Code echo command allowed bypass of user approval prompt for command execution","id":"CVE-2025-54795","kev_date_added":null,"published":"2025-08-05"},{"cvss_score":7.7,"headline":"Claude Code: Sandbox Escape via Git Worktree Path Confusion Allows Unsandboxed Code Execution","id":"CVE-2026-55607","kev_date_added":null,"published":"2026-06-29"}],"sources":[{"class":"attribution","licence":"CVE Terms of Use (MITRE)","name":"CVE List","prefix":"CVE"},{"class":"attribution","licence":"CC BY 4.0","name":"GitHub Advisory Database","prefix":"GHSA"},{"class":"attribution","licence":"US public information, NVD API terms","name":"NVD"},{"class":"attribution","licence":"CWE Terms of Use","name":"CWE (MITRE)"},{"class":"attribution","licence":"FIRST CVSS licence","name":"CVSS (FIRST)"},{"class":"open","licence":"CC0","name":"PoC-in-GitHub"}],"ssvc":{"automatable":"no","exploitation":"none","technical_impact":"total"},"state":"PUBLISHED","updated":"2025-10-03","vendors":["anthropics"]},"summary":"Attackers can execute arbitrary code by tricking users into starting Claude Code in a malicious directory before accepting the trust dialog.","url":"https://insights.sbomify.com/CVE-2025-59536/"}