Vulnerabilityhigh

Claude Code Flaws Allow Remote Code Execution and API Key Exfiltration

The Hacker Newsby @TheHackersNewsFeb 26, 2026 · 05:59 UTC (Feb 26, 2026)2 min read4

Read at thehackernews.com

Analyze CVE-2025-59536 with Vani AIImpact, affected versions, exploitation, mitigations and detection

CVEs: CVE-2025-59536 CVE-2026-21852

Tags: cve-2025-59536 cve-2026-21852 vulnerability

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%		Oct 3, 2025
CVE-2026-21852	API Key Exfiltration via Attacker-Controlled Base URL in Anthropic Claude Code	5.3	25%		Jan 21, 2026

From the original article

2 min read at thehackernews.com

 Ravie Lakshmanan  Feb 25, 2026 Artificial Intelligence / Vulnerability Cybersecurity researchers have disclosed multiple security vulnerabilities in Anthropic's Claude Code, an artificial intelligence (AI)-powered coding assistant, that could result in remote code execution and theft of API credentials.

The Hacker News

By @TheHackersNews · thehackernews.com

Read the full article at The Hacker News

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.