CyberHappenings logo
☰
Home Browse Watchlists Experimental About

Track cybersecurity events as they unfold. Sourced timelines. Filter, sort, and browse. Fast, privacy‑respecting. No invasive ads, no tracking.

Claude Code Vulnerabilities Enable Remote Code Execution and API Key Theft

First reported
Last updated
1 unique sources, 1 articles

Summary

Hide ▲

Multiple vulnerabilities in Anthropic's Claude Code AI-powered coding assistant allow remote code execution and API key exfiltration. The flaws exploit configuration mechanisms, including Hooks, Model Context Protocol (MCP) servers, and environment variables. Three vulnerabilities were identified, with fixes released in versions 1.0.87, 1.0.111, and 2.0.65. Exploitation could lead to arbitrary code execution, data exfiltration, and unauthorized access to AI infrastructure. The vulnerabilities highlight the risks associated with AI-powered tools that execute commands and initiate network communication autonomously.

Timeline

  1. 25.02.2026 19:00 1 articles · 3h ago

    Claude Code Vulnerabilities Disclosed and Patched

    Multiple vulnerabilities in Claude Code were disclosed, enabling remote code execution and API key exfiltration. The vulnerabilities were fixed in versions 1.0.87 (September 2025), 1.0.111 (October 2025), and 2.0.65 (January 2026). Exploitation could lead to unauthorized access to AI infrastructure, data exfiltration, and financial costs. The flaws highlight the risks associated with AI-powered tools that execute commands and initiate network communication autonomously.

    Show sources
    Open in new tab

Information Snippets

  • No CVE (CVSS score: 8.7) - Code injection vulnerability allowing arbitrary code execution via untrusted project hooks in .claude/settings.json. Fixed in version 1.0.87 (September 2025).

    First reported: 25.02.2026 19:00
    1 source, 1 article
    Show sources

  • CVE-2025-59536 (CVSS score: 8.7) - Code injection vulnerability enabling arbitrary shell command execution upon tool initialization in untrusted directories. Fixed in version 1.0.111 (October 2025).

    First reported: 25.02.2026 19:00
    1 source, 1 article
    Show sources

  • CVE-2026-21852 (CVSS score: 5.3) - Information disclosure vulnerability allowing API key exfiltration via malicious repositories. Fixed in version 2.0.65 (January 2026).

    First reported: 25.02.2026 19:00
    1 source, 1 article
    Show sources

  • Exploitation could lead to unauthorized access to shared project files, modification/deletion of cloud-stored data, and generation of unexpected API costs.

    First reported: 25.02.2026 19:00
    1 source, 1 article
    Show sources

  • Vulnerabilities exploit configuration files (.mcp.json and .claude/settings.json) to override user approval and execute commands autonomously.

    First reported: 25.02.2026 19:00
    1 source, 1 article
    Show sources