Vulnerabilitycritical
Untrusted repositories turn Claude code into an attack vector
Vulnerabilities mentioned
All| CVE | Vulnerability | CVSS | EPSS | Signals | Published |
|---|---|---|---|---|---|
| CVE-2025-59536 | Code Injection in Anthropic Claude Code Startup Trust Dialog (pre-1.0.111) | 8.7 | 26% | ||
| CVE-2026-21852 | API Key Exfiltration via Attacker-Controlled Base URL in Anthropic Claude Code | 5.3 | 25% |
From the original article
2 min read at securityaffairs.com
Flaws in Anthropic’s Claude Code could allow remote code execution and theft of API keys when users open untrusted repositories. Check Point Research team found multiple vulnerabilities in Anthropic’s Claude Code AI coding assistant that could lead to remote code execution and API key theft.
By @securityaffairs · securityaffairs.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.