CVE-2026-21852
Claude Code Leaks Data via Malicious Environment Configuration Before Trust Confirmation
Description
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 ANTHROPIC_BASE_URL to an attacker-controlled endpoint and when the repository was opened, Claude Code would read the configuration and immediately issue API requests before showing the trust prompt, potentially leaking the user's API keys. Users on standard Claude Code auto-update have received this fix already. Users performing manual updates are advised to update to version 2.0.65, which contains a patch, or to the latest version.
INFO
Published Date :
Jan. 21, 2026, 9:16 p.m.
Last Modified :
Feb. 2, 2026, 3:04 p.m.
Remotely Exploit :
Yes !
Source :
[email protected]
CVSS Scores
| Score | Version | Severity | Vector | Exploitability Score | Impact Score | Source |
|---|---|---|---|---|---|---|
| CVSS 3.1 | HIGH | [email protected] | ||||
| CVSS 4.0 | MEDIUM | [email protected] |
Solution
- Update Claude Code to version 2.0.65.
- Use the latest version for enhanced security.
- Avoid opening untrusted repositories.
Public PoC/Exploit Available at Github
CVE-2026-21852 has a 37 public
PoC/Exploit available at Github.
Go to the Public Exploits tab to see the list.
References to Advisories, Solutions, and Tools
Here, you will find a curated list of external links that provide in-depth
information, practical solutions, and valuable tools related to
CVE-2026-21852.
| URL | Resource |
|---|---|
| https://github.com/anthropics/claude-code/security/advisories/GHSA-jh7p-qr78-84p7 | Vendor Advisory |
CWE - Common Weakness Enumeration
While CVE identifies
specific instances of vulnerabilities, CWE categorizes the common flaws or
weaknesses that can lead to vulnerabilities. CVE-2026-21852 is
associated with the following CWEs:
Common Attack Pattern Enumeration and Classification (CAPEC)
Common Attack Pattern Enumeration and Classification
(CAPEC)
stores attack patterns, which are descriptions of the common attributes and
approaches employed by adversaries to exploit the CVE-2026-21852
weaknesses.
We scan GitHub repositories to detect new proof-of-concept exploits. Following list is a collection of public exploits and proof-of-concepts, which have been published on GitHub (sorted by the most recently updated).
A practitioner-focused reference for AI/ML security — attacks, tools, research, and defenses. Covers offensive AI, securing AI systems, AI-assisted security operations, and governance.
Michael Adams — Security Specialist Agent. Diagnosis-only cybersecurity agent for Claude Code with persistent memory, STRIDE threat modeling, and OWASP framework mappings.
Shell
AI agent behavioral alignment benchmark — measuring what agents do beyond what they're asked
Python JavaScript HTML Shell
Security monitor for AI coding agents — detect hook RCE, MCP poisoning, and API key theft
ai-agents claude-code cli copilot cursor cybersecurity devtools llm-security mcp prompt-injection python security
Python
A curated timeline of real AI agent security incidents, breaches, and vulnerabilities (2024-2026). Every entry sourced and dated.
ai-agent-security ai-agents ai-security awesome-list cybersecurity llm-security mcp-security prompt-injection supply-chain-security
SSG governance rules — claude-code (AI safety)
Security scanner for MCP-connected AI agent pipelines — 77 rules, 13 scanners, OWASP Agentic 10/10, GitHub Action, SARIF, compliance mapping
ai-agent ai-security claude-code github-action mcp mcp-security owasp sarif scanner security supply-chain-security tool-poisoning ai-agent-security ai-safety security-scanner static-analysis
Python Dockerfile Shell TypeScript
Supply-chain security for Claude Code plugins — detects marketplace auto-updates and surfaces security-relevant diffs
Python
AIDE Security Scanner - Detects malicious configurations in Claude Code, Cursor, Windsurf, Aider
Python Shell Dockerfile
A modular cybersecurity guide mapping prompt injection attack surfaces across all Claude environments
Python Shell
Claude Code security plugin: deny rules, PreToolUse hooks, OS sandbox, and Docker isolation. Based on real CVEs and sandbox escape research.
claude-code plugin security
Security MCP for vibe coding. 334 rules, 31 tools for Next.js, Supabase, Clerk, Stripe, Prisma, tRPC, Hono, GraphQL, Convex, Turso, Uploadthing, AI SDK, and the full AI-generated stack.
ai-security claude clerk cursor mcp nextjs owasp prisma sast security stripe supabase typescript vercel vibe-coding gemini-cli-extension
TypeScript JavaScript
macOS containment for AI agents — user isolation, kernel sandbox, pf firewall, DNS blocklist, backup/rollback. TLA+ verified.
ai-agents claude-code cli containment developer-tools formal-verification go macos pf-firewall sandbox seatbelt security tla-plus
Shell Python Go Makefile TLA Ruby
Zero-knowledge credential proxy for AI agents. Use AI, with Zero trust.
Go Dockerfile HCL JavaScript CSS HTML TypeScript Shell
Is your skill a security risk?
ai-safety audit claude-code extensions hooks mcp privacy security skills supply-chain telemetry
TypeScript
Results are limited to the first 15 repositories due to potential performance issues.
The following list is the news that have been mention
CVE-2026-21852 vulnerability anywhere in the article.
-
TheCyberThrone
Claude Code Security vs. OpenAI Codex Security – AI Arms Race
A Technical Comparison for AppSec Engineers | March 2026TL;DRBoth tools launched within two weeks of each other in early 2026. Both use LLM-driven reasoning to find and patch vulnerabilities beyond wh ... Read more
-
CybersecurityNews
Claude Code Hacked to Achieve Full RCE and Hijacked Organization API keys
Claude Code Hacked RCE Hijacked Organization API keys Critical vulnerabilities in Anthropic’s Claude Code, an AI-powered command-line development tool. The flaws could allow attackers to achieve Remot ... Read more
-
CybersecurityNews
Critical Claude Code Vulnerabilities Enables Remote Code Execution Attacks
Claude Code Vulnerabilities A critical security flaw in Anthropic’s Claude Code demonstrates how threat actors can exploit repository configuration files to execute malicious code and steal sensitive ... Read more
-
The Register
Claude collaboration tools left the door wide open to remote code execution
Security vulnerabilities in Claude Code could have allowed attackers to remotely execute code on users' machines and steal API keys by injecting malicious configurations into repositories, and then wa ... Read more
-
The Hacker News
Claude Code Flaws Allow Remote Code Execution and API Key Exfiltration
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 execut ... Read more
The following table lists the changes that have been made to the
CVE-2026-21852 vulnerability over time.
Vulnerability history details can be useful for understanding the evolution of a vulnerability, and for identifying the most recent changes that may impact the vulnerability's severity, exploitability, or other characteristics.
-
Initial Analysis by [email protected]
Feb. 02, 2026
Action Type Old Value New Value Added CVSS V3.1 AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N Added CPE Configuration OR *cpe:2.3:a:anthropic:claude_code:*:*:*:*:*:node.js:*:* versions up to (excluding) 2.0.65 Added Reference Type GitHub, Inc.: https://github.com/anthropics/claude-code/security/advisories/GHSA-jh7p-qr78-84p7 Types: Vendor Advisory -
New CVE Received by [email protected]
Jan. 21, 2026
Action Type Old Value New Value Added Description 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 ANTHROPIC_BASE_URL to an attacker-controlled endpoint and when the repository was opened, Claude Code would read the configuration and immediately issue API requests before showing the trust prompt, potentially leaking the user's API keys. Users on standard Claude Code auto-update have received this fix already. Users performing manual updates are advised to update to version 2.0.65, which contains a patch, or to the latest version. Added CVSS V4.0 AV:N/AC:L/AT:N/PR:N/UI:P/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X Added CWE CWE-522 Added Reference https://github.com/anthropics/claude-code/security/advisories/GHSA-jh7p-qr78-84p7