CVE-2026-21852

Claude Code is an agentic coding tool. Prior to version 2.0.65, vulnerability in Claude Code's project-load flow allowed malicious repositories to exfiltrate data including Anthropic API keys before users confirmed trust. An attacker-controlled repository could include a settings file that sets...

CVE-2026-21852

Claude Code is an agentic coding tool. Prior to version 2.0.65, vulnerability in Claude Code's project-load flow allowed malicious repositories to exfiltrate data including Anthropic API keys before users confirmed trust. An attacker-controlled repository could include a settings file that sets...

CVE-2026-21852

CVE-2026-21852 affects Claude Code prior to 2.0.65. The vulnerability resides in the project-load flow where an attacker-controlled repository can set ANTHROPIC_BASE_URL to an attacker endpoint, causing Claude Code to issue API requests and leak Anthropic API keys before trust confirmation. Impac...

CVE-2026-21852

Claude Code is an agentic coding tool. Prior to version 2.0.65, vulnerability in Claude Code's project-load flow allowed malicious repositories to exfiltrate data including Anthropic API keys before users confirmed trust. An attacker-controlled repository could include a settings file that sets...

CVE-2026-21852 Claude Code Leaks Data via Malicious Environment Configuration Before Trust Confirmation

Claude Code is an agentic coding tool. Prior to version 2.0.65, vulnerability in Claude Code's project-load flow allowed malicious repositories to exfiltrate data including Anthropic API keys before users confirmed trust. An attacker-controlled repository could include a settings file that sets...

CVE-2026-21852 Claude Code Leaks Data via Malicious Environment Configuration Before Trust Confirmation

Claude Code is an agentic coding tool. Prior to version 2.0.65, vulnerability in Claude Code's project-load flow allowed malicious repositories to exfiltrate data including Anthropic API keys before users confirmed trust. An attacker-controlled repository could include a settings file that sets...

CVE-2026-21852 Claude Code Leaks Data via Malicious Environment Configuration Before Trust Confirmation

Claude Code is an agentic coding tool. Prior to version 2.0.65, vulnerability in Claude Code's project-load flow allowed malicious repositories to exfiltrate data including Anthropic API keys before users confirmed trust. An attacker-controlled repository could include a settings file that sets...

Claude Code Leaks Data via Malicious Environment Configuration Before Trust Confirmation

A vulnerability in Claude Code's project-load flow allowed malicious repositories to exfiltrate data including Anthropic API keys before users confirmed trust. If a user started Claude Code in an attacker-controller repository, and the repository included a settings file that set ANTHROPICBASEURL...

GHSA-JH7P-QR78-84P7 Claude Code Leaks Data via Malicious Environment Configuration Before Trust Confirmation

A vulnerability in Claude Code's project-load flow allowed malicious repositories to exfiltrate data including Anthropic API keys before users confirmed trust. If a user started Claude Code in an attacker-controller repository, and the repository included a settings file that set ANTHROPICBASEURL...

1shot (>=0.0.3 <=0.0.9), @4via6/relay (>=1.0.0 <=1.1.3) +234 more potentially affected by CVE-2026-21852 via @anthropic-ai/claude-code (>=0.2.126 <=2.0.64)

@anthropic-ai/claude-code NPM version =0.2.126, =0.0.3, =1.0.0, =0.1.18, =1.0.0, =0.4.0, =0.2.3, =0.0.1, =0.0.1, =0.0.55, =0.0.69 - @brandongtr/rule-agent-cli =1.0.1-beta.0 and more Source cves: CVE-2026-21852 Source advisory: OSV:GHSA-JH7P-QR78-84P7...

@kimuson/claude-code-viewer (>=0.4.2 <=0.5.9), @netlify/agent-runner-cli (>=1.31.0 <=1.58.1-alpha) +14 more potentially affected by CVE-2026-21852 via @anthropic-ai/claude-code (>=2.0.0 <=2.0.64)

@anthropic-ai/claude-code NPM version =2.0.0, =0.4.2, =1.31.0, =0.0.1-rc.1, =0.12.0, =0.5.2, =0.12.1, =0.0.0, =0.1.2, =0.11.1, =0.11.0, =1.0.0, =0.10.2, =0.11.5-2 and more Source cves: CVE-2026-21852 Source advisory: SNYK:JS-ANTHROPICAICLAUDECODE-15046268...

Insufficiently Protected Credentials

Overview @anthropic-ai/claude-code is an Use Claude, Anthropic's AI assistant, right from your terminal. Claude can understand your codebase, edit files, run terminal commands, and handle entire workflows for you. Affected versions of this package are vulnerable to Insufficiently Protected...

PT-2026-3758

Name of the Vulnerable Software and Affected Versions Claude Code versions prior to 2.0.65 Description A flaw in the project-load flow of Claude Code allows malicious repositories to exfiltrate sensitive data, such as Anthropic API keys, before a user confirms trust. An attacker can achieve this ...

Claude Code security vulnerabilities

Claude Code is an open-source proxy encoding tool developed by Anthropic. Versions of Claude Code prior to 2.0.65 contained security vulnerabilities. These vulnerabilities stemmed from the project’s loading process, which allowed malicious repositories to leak data before the user confirmed trust...

ntree

NTREE v2.0 - Neural Tactical Red-Team Exploitation Engine C...

AI-Vuln-Reproduce

AI-Vuln-Reproduce AI Fully Automated Vulnerability Reproducti...

RAPTOR - Autonomous Offensive/Defensive Security Research Framework

RAPTOR is an autonomous offensive/defensive security research framework, based on Claude Code. It empowers security research with agentic workflows and automation. RAPTOR stands for Recursive Autonomous Penetration Testing and Observation Robot...

Automated Penetration Testing with LLM Agents and Classical Planning

While penetration testing plays a vital role in cybersecurity, achieving fully automated, hands-off-the-keyboard execution remains a significant research challenge. In this paper, we introduce the "Planner-Executor-Perceptor PEP" design paradigm and use it to systematically review existing work a...

Claude Code Code Execution Vulnerability

Claude Code is a smart endpoint programming assistant that understands code bases and helps improve development efficiency through natural language commands that perform routine tasks, interpret complex code, handle Git workflows, and more, allowing developers to complete coding operations with...

CVE-2025-66032

Claude Code is an agentic coding tool. Prior to 1.0.93, Due to errors in parsing shell commands related to $IFS and short CLI flags, it was possible to bypass the Claude Code read-only validation and trigger arbitrary code execution. Reliably exploiting this requires the ability to add untrusted...