CVE-2025-66479

CVE

Threat entity extracted from intelligence sources

Frequency

4

occurrences

First Seen

May 20, 2026

Last Seen

May 21, 2026

Exploited in Wild

—

Ransomware Use

—

Public Exploits

—

Attack Vector

—

Vulnerability Overview

Exploitation Activity

Exploitation Intelligence

Critical Sandbox Bypass in Claude Code Exposes User Data71.0

Anthropic's Claude Code AI platform has been found to have a critical network sandbox bypass vulnerability, allowing attackers to exfiltrate sensitive data, including user credentials and source code. Discovered by researcher Aonan Guan, this flaw is the second complete bypass identified within six...

Public Exploits

Checking GitHub for proof-of-concept code…

Related Clusters (1)

Critical Sandbox Bypass in Claude Code Exposes User Data

May 20·7 sources

Related Articles (4)

Anthropic fixes another Claude Code security bypass without telling users

Cybernews·May 21

Anthropic Sandbox Cve 2025 66479

oddguan.com·May 20

Second Time Same Sandbox Anthropic Claude Code Network Allowlist Bypass Data Exfiltration

oddguan.com·May 20

Even Claude agrees: hole in its sandbox was real and dangerous

Theregister·May 20

Related Entities

Data Breach Data Exfiltration Anthropic CWE-200 - Exposure of Sensitive Information T1041 - Exfiltration Over C2 Channel T1567 - Exfiltration Over Web Service GitHub Linux MacOS Sandbox-runtime Claude Code Netcat