What is 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.
The record classifies CVE-2025-59536 under weakness class CWE-94. Its CVSS v3 base vector states that the flaw is reachable remotely over the network, needs no prior authentication, needs a user to take an action first, and has high impact on confidentiality, integrity, availability. 1 affected-product entry is recorded, across 1 vendor, listed below. The identifier was first published 390 days ago.
Severity and exploitation probability
- CVSS v3.1 base score
- 8.8 — HIGH
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H - CVSS v4.0 base score
- 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 - EPSS (FIRST)
- 27.2% probability of exploitation in the next 30 days, higher than 98.0% of all scored CVEs
- CISA KEV
- Not listed in the CISA Known Exploited Vulnerabilities catalog
- Threadlinqs priority
- 10/10 — a Threadlinqs composite of the CVSS base score, the EPSS percentile and public exploit availability
- Published
- 2025-10-03
Is CVE-2025-59536 being exploited?
Weaponised exploit code for CVE-2025-59536 is publicly available. 6 public proof-of-concept repositories are tracked for this identifier. It currently carries a trending score of 38 in the Threadlinqs vulnerability feed.
- AetherAI3/AETHER-PROTOCOL-P (github)
- Rohitberiwala/Claude-Code-MCP-Injection-PoC (github)
- NetVanguard-cmd/CVE-2025-59536 (github)
- TreRB/ai-ide-config-guard (github)
- Razi-Interactive/claude-project-scanner (github)
- Perufitlife/dotclaude-security (github)
Affected products and versions
- Anthropic: Claude Code
Affected software packages:
npm:@anthropic-ai/claude-code— patched in 1.0.111
How to fix CVE-2025-59536
The record marks a vendor fix as available for CVE-2025-59536. Fixed versions are recorded for 1 package: npm:@anthropic-ai/claude-code 1.0.111. Patch reference: https://github.com/anthropics/claude-code/security/advisories/GHSA-4fgq-fpq9-mr3g. Vendor advisory: https://github.com/anthropics/claude-code/security/advisories/GHSA-4fgq-fpq9-mr3g. Apply the vendor fix referenced above to every affected product listed in this record, then confirm the running version against the vendor advisory.
Threat activity tracking CVE-2025-59536
3 tracked threats in the Threadlinqs corpus reference CVE-2025-59536, either in the campaign’s CVE list or as an indicator on the campaign record.
- NVIDIA Releases SkillSpector: Open-Source Security Scanner for AI Agent Skills — LOW · 2026-08-03
- Internet-Wide Reconnaissance Scans Target MCP Servers and Claude/Cursor AI-Agent Credentials — MEDIUM · 2026-07-13
- Claude Code RCE & API Key Exfiltration — CVE-2025-59536 + CVE-2026-21852, Untrusted Repo Attack Surface via Hooks, MCP Servers & Environment Variables — HIGH · 2026-02-26
Sources
Enriched from CVE.org, FIRST EPSS, GitHub Security Advisories, public proof-of-concept repositories. Last verified by Threadlinqs on .