PT-2026-29378

The Claude SDK for Python provides access to the Claude API from Python applications. From version 0.86.0 to before version 0.87.0, the local filesystem memory tool in the Anthropic Python SDK created memory files with mode 0o666, leaving them world-readable on systems with a standard umask and...

PT-2026-29380

The Claude SDK for Python provides access to the Claude API from Python applications. From version 0.86.0 to before version 0.87.0, the async local filesystem memory tool in the Anthropic Python SDK validated that model-supplied paths resolved inside the sandboxed memory directory, but then...

Claude SDK for Python 安全漏洞

Claude SDK for Python is an open-source Python software development toolkit developed by Anthropic for calling the Claude API. Versions of Claude SDK for Python prior to 0.87.0 contained a security vulnerability. This vulnerability stemmed from improper file permission settings created by memory...

Claude SDK for TypeScript 安全漏洞

Claude SDK for TypeScript is an open-source development toolkit by Anthropic, designed for calling the Claude API using TypeScript. Versions of Claude SDK for TypeScript prior to 0.81.0 contain security vulnerabilities. These vulnerabilities stem from insufficient validation of model-provided pat...

PT-2026-29379

Claude SDK for TypeScript provides access to the Claude API from server-side TypeScript or JavaScript applications. From version 0.79.0 to before version 0.81.0, the local filesystem memory tool in the Anthropic TypeScript SDK validated model-supplied paths using a string prefix check that did no...

PT-2026-29282

Uncontrolled search path elements in Anthropic Claude for Windows installer Claude Setup.exe versions prior to 1.1.3363 allow local privilege escalation via DLL search-order hijacking. The installer loads DLLs e.g., profapi.dll from its own directory after UAC elevation, enabling arbitrary code...

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 1.1.3363 contained a security vulnerability, which was caused by uncontrolled search path elements, potentially leading to local privilege escalation...

test-xss

test-xss "test." Install bash np...

Kill-Chain Canaries: Stage-Level Tracking of Prompt Injection across Attack Surfaces and Model Safety Tiers

We present a stage-decomposed analysis of prompt injection attacks against five frontier LLM agents. Prior work measures task-level attack success rate ASR; we localize the pipeline stage at which each model's defense activates. We instrument every run with a cryptographic canary token...

pentest-ai

pentest-ai Turn Claude Code into your offensive security re...

CVE-2025-15060

claude-hovercraft executeClaudeCode Command Injection Remote Code Execution Vulnerability. This vulnerability allows remote attackers to execute arbitrary code on affected installations of claude-hovercraft. Authentication is not required to exploit this vulnerability. The specific flaw exists...

CVE-2026-33068

Claude Code is an agentic coding tool. Versions prior to 2.1.53 resolved the permission mode from settings files, including the repo-controlled .claude/settings.json, before determining whether to display the workspace trust confirmation dialog. A malicious repository could set...

Claude Extension Flaw Enabled Zero-Click XSS Prompt Injection via Any Website

Cybersecurity researchers have disclosed a vulnerability in Anthropic's Claude Google Chrome Extension that could have been exploited to trigger malicious prompts simply by visiting a web page. The flaw "allowed any website to silently inject prompts into that assistant as if the user wrote them,...

CVE-2026-33068

Claude Code is an agentic coding tool. Versions prior to 2.1.53 resolved the permission mode from settings files, including the repo-controlled .claude/settings.json, before determining whether to display the workspace trust confirmation dialog. A malicious repository could set...

CVE-2026-33068

Claude Code is an agentic coding tool. Versions prior to 2.1.53 resolved the permission mode from settings files, including the repo-controlled .claude/settings.json, before determining whether to display the workspace trust confirmation dialog. A malicious repository could set...

CVE-2026-33068 Claude Code has a Workspace Trust Dialog Bypass via Repo-Controlled Settings File

Claude Code is an agentic coding tool. Versions prior to 2.1.53 resolved the permission mode from settings files, including the repo-controlled .claude/settings.json, before determining whether to display the workspace trust confirmation dialog. A malicious repository could set...

CVE-2026-33068 Claude Code has a Workspace Trust Dialog Bypass via Repo-Controlled Settings File

Claude Code is an agentic coding tool. Versions prior to 2.1.53 resolved the permission mode from settings files, including the repo-controlled .claude/settings.json, before determining whether to display the workspace trust confirmation dialog. A malicious repository could set...

CVE-2026-33068 Claude Code has a Workspace Trust Dialog Bypass via Repo-Controlled Settings File

Claude Code is an agentic coding tool. Versions prior to 2.1.53 resolved the permission mode from settings files, including the repo-controlled .claude/settings.json, before determining whether to display the workspace trust confirmation dialog. A malicious repository could set...

CVE-2026-33068

CVE-2026-33068 affects Claude Code. Versions prior to 2.1.53 could bypass the workspace trust dialog by using permissions.defaultMode set to bypassPermissions in the repo-controlled .claude/settings.json, allowing silent trust mode on first open and enabling tool execution without user consent. T...

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 2.1.53 contained a security vulnerability, which was caused by improper order of permission mode parsing. This vulnerability could potentially allow bypassing the workspace...