CVE-2026-35603

CVE-2026-35603 (Claude Code, Windows) : In versions prior to 2.1.75, Claude Code loaded the system-wide default configuration from C:\ProgramData\ClaudeCode\managed-settings.json without validating directory ownership or access permissions. Since ProgramData is writable by non-administrative user...

CVE-2026-35603 Claude Code: Insecure System-Wide Configuration Loading Enables Local Privilege Escalation on Windows

Claude Code is an agentic coding tool. In versions prior to 2.1.75 on Windows, Claude Code loaded the system-wide default configuration from C:\ProgramData\ClaudeCode\managed-settings.json without validating directory ownership or access permissions. Because the ProgramData directory is writable ...

CVE-2026-35603 Claude Code: Insecure System-Wide Configuration Loading Enables Local Privilege Escalation on Windows

Claude Code is an agentic coding tool. In versions prior to 2.1.75 on Windows, Claude Code loaded the system-wide default configuration from C:\ProgramData\ClaudeCode\managed-settings.json without validating directory ownership or access permissions. Because the ProgramData directory is writable ...

Claude Code 安全漏洞

Claude Code is an open-source terminal-native AI programming tool developed by Anthropic. Versions of Claude Code prior to 2.1.75 contained a security vulnerability. This vulnerability stemmed from the lack of verification of directory ownership or access permissions when loading system-wide...

@paperclipai/server (>=2026.3.17-canary.2 <=2026.416.0-canary.1), companies.sh (>=2026.324.0-canary.0 <=2026.325.0-canary.3) +4 more potentially affected by unknown CVE via @paperclipai/adapter-claude-local (>=2026.318.0-canary.0 <=2026.416.0-canary.1)

@paperclipai/adapter-claude-local NPM version =2026.318.0-canary.0, =2026.3.17-canary.2, =2026.324.0-canary.0, =2026.3.17-canary.3, =0.6.5, =0.6.6 Source cves: unknown CVE Source advisory: SNYK:JS-PAPERCLIPAIADAPTERCLAUDELOCAL-16421446...

Fake Claude AI Installer Targets Windows Users with PlugX Malware

Fake Claude AI installer mimicking Anthropic spreads PlugX malware on Windows, using DLL sideloading to gain persistent remote access to infected systems...

EUVD-2026-22293

Claude Code has a Domain Validation Bypass which Allows Automatic Requests to Attacker-Controlled Domains...

Honeypot Protocol

Trusted monitoring, the standard defense in AI control, is vulnerable to adaptive attacks, collusion, and strategic attack selection. All of these exploit the fact that monitoring is passive: it observes model behavior but never probes whether the model would behave differently under different...

Hacker Used Claude Code, GPT-4.1 to Exfiltrate Hundreds of Millions of Mexican Records

A lone hacker used Claude Code and GPT-4.1 to exfiltrate hundreds of millions of Mexican citizen records from 9 government agencies...

Fake Claude site installs malware that gives attackers access to your computer

Claude’s rapid growth—nearly 290 million web visits per month—has made it an attractive target for attackers, and this campaign shows how easy it is to fall for a fake site. We discovered a fake website impersonating Anthropic’s Claude to serve a trojanized installer. The domain mimics Claude's...

Sen. Sanders Talks to Claude About AI and Privacy

Claude is actually pretty good on the issues...

Anthropic Claude Code < 2.1.2 Sandbox Escape via settings.json Injection (CVE-2026-25725)

The version of Anthropic Claude Code installed on the remote host is prior to 2.1.2. It is, therefore, affected by a sandbox escape vulnerability. The bubblewrap sandboxing mechanism failed to properly protect the .claude/settings.json configuration file when it did not exist at startup. While th...

Anthropic Claude Code < 2.0.65 API Key Leak via Project Settings (CVE-2026-21852)

The version of Anthropic Claude Code installed on the remote host is prior to 2.0.65. It is, therefore, affected by an information disclosure vulnerability. A vulnerability in the project-load flow allowed malicious repositories to exfiltrate data including Anthropic API keys before users confirm...

Anthropic Claude Code < 2.1.7 Permission Deny Bypass Through Symbolic Links (CVE-2026-25724)

The version of Anthropic Claude Code installed on the remote host is prior to 2.1.7. It is, therefore, affected by a permission bypass vulnerability. Claude Code failed to strictly enforce deny rules configured in settings.json when accessing files through symbolic links. If a user explicitly...

Claude Code Can Be Manipulated via CLAUDE.md to Run SQL Injection Attacks

LayerX researchers have discovered how to bypass Claude Code’s safety rules using the CLAUDE.md file. This exploit allows…...

Vulnerability Detection with Interprocedural Context in Multiple Languages: Assessing Effectiveness and Cost of Modern LLMs

Large Language Models LLMs have been a promising way for automated vulnerability detection. However, most prior studies have explored the use of LLMs to detect vulnerabilities only within single functions, disregarding those related to interprocedural dependencies. These studies overlook...

Anthropic's Claude Mythos Finds Thousands of Zero-Day Flaws Across Major Systems

Artificial Intelligence AI company Anthropic announced a new cybersecurity initiative called Project Glasswing that will use a preview version of its new frontier model, Claude Mythos , to find and address security vulnerabilities. The model will be used by a small set of organizations, including...

openclaw-claude-bridge: sandbox is not effective - `--allowed-tools ""` does not restrict available tools

Affected openclaw-claude-bridge v1.1.0 Issue v1.1.0 spawns the Claude Code CLI subprocess with --allowed-tools "" and the release notes + README claim this "disables all CLI tools" for sandboxing. This claim is incorrect. Per the Claude Code CLI documentation, --allowed-tools alias --allowedTools...

GHSA-7853-GQQM-VCWX openclaw-claude-bridge: sandbox is not effective - `--allowed-tools ""` does not restrict available tools

Affected openclaw-claude-bridge v1.1.0 Issue v1.1.0 spawns the Claude Code CLI subprocess with --allowed-tools "" and the release notes + README claim this "disables all CLI tools" for sandboxing. This claim is incorrect. Per the Claude Code CLI documentation, --allowed-tools alias --allowedTools...

PT-2026-31279

Affected openclaw-claude-bridge v1.1.0 Issue v1.1.0 spawns the Claude Code CLI subprocess with --allowed-tools "" and the release notes + README claim this "disables all CLI tools" for sandboxing. This claim is incorrect. Per the Claude Code CLI documentation, --allowed-tools alias --allowedTools...