CVE-2026-10223

A weakness has been identified in NousResearch hermes-agent up to 2026.4.30. This affects the function scanmemorycontent of the file tools/memorytool.py. This manipulation causes injection. The attack can be initiated remotely. The exploit has been made available to the public and could be used f...

CVE-2026-10223

A weakness has been identified in NousResearch hermes-agent up to 2026.4.30. This affects the function scanmemorycontent of the file tools/memorytool.py. This manipulation causes injection. The attack can be initiated remotely. The exploit has been made available to the public and could be used f...

CVE-2026-10223

A weakness has been identified in NousResearch hermes-agent up to 2026.4.30. This affects the function scanmemorycontent of the file tools/memorytool.py. This manipulation causes injection. The attack can be initiated remotely. The exploit has been made available to the public and could be used f...

CVE-2026-10223 NousResearch hermes-agent memory_tool.py _scan_memory_content injection

A weakness has been identified in NousResearch hermes-agent up to 2026.4.30. This affects the function scanmemorycontent of the file tools/memorytool.py. This manipulation causes injection. The attack can be initiated remotely. The exploit has been made available to the public and could be used f...

EUVD-2026-33556

A weakness has been identified in NousResearch hermes-agent up to 2026.4.30. This affects the function scanmemorycontent of the file tools/memorytool.py. This manipulation causes injection. The attack can be initiated remotely. The exploit has been made available to the public and could be used f...

CVE-2026-10223

CVE-2026-10223 affects NousResearch hermes-agent up to version 2026.4.30. The weakness is in tools/memory_tool.py function _scan_memory_content, enabling remote injection. CVSS metrics indicate NETWORK access, LOW attack complexity, and LOW privileges required, with PROOF-OF-CONCEPT exploit matur...

CVE-2026-10223 NousResearch hermes-agent memory_tool.py _scan_memory_content injection

A weakness has been identified in NousResearch hermes-agent up to 2026.4.30. This affects the function scanmemorycontent of the file tools/memorytool.py. This manipulation causes injection. The attack can be initiated remotely. The exploit has been made available to the public and could be used f...

Hermes Agent security vulnerabilities

Hermes Agent is an AI agent tool developed by Nous Research, featuring a self-learning mechanism. Versions of Hermes Agent prior to 2026.4.30 contained a security vulnerability, which was caused by a problem with the scanmemorycontent function in the tools/memorytool.py file. This vulnerability...

CVE-2026-44111

OpenClaw before 2026.4.15 contains an arbitrary file read vulnerability in the QMD backend memoryget function that allows callers to read any Markdown files within the workspace root. Attackers with access to the memory tool can bypass path restrictions by providing arbitrary workspace Markdown...

CVE-2026-41686

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 0.91.1, the BetaLocalFilesystemMemoryTool in the Anthropic TypeScript SDK created memory files and directories using the Node.js default modes...

CVE-2026-41686

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 0.91.1, the BetaLocalFilesystemMemoryTool in the Anthropic TypeScript SDK created memory files and directories using the Node.js default modes...

CVE-2026-41686 Claude SDK for TypeScript has Insecure Default File Permissions in Local Filesystem Memory Tool

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 0.91.1, the BetaLocalFilesystemMemoryTool in the Anthropic TypeScript SDK created memory files and directories using the Node.js default modes...

CVE-2026-41686 Claude SDK for TypeScript has Insecure Default File Permissions in Local Filesystem Memory Tool

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 0.91.1, the BetaLocalFilesystemMemoryTool in the Anthropic TypeScript SDK created memory files and directories using the Node.js default modes...

CVE-2026-41686

The CVE-2026-41686 entry concerns the Claude SDK for TypeScript, where the BetaLocalFilesystemMemoryTool from Anthropic’s TypeScript SDK (versions 0.79.0 through before 0.91.1) created memory files with default Node.js modes (files 0o666, dirs 0o777). This caused world-readable files on normal um...

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. There were security vulnerabilities in versions of Claude SDK for TypeScript from 0.79.0 to 0.91.1. These vulnerabilities stemmed from BetaLocalFilesystemMemoryTool...

Your LLM Agent Can Leak Your Data: Data Exfiltration Via Backdoored Tool Use

Tool-use large language model LLM agents are increasingly deployed to support sensitive workflows, relying on tool calls for retrieval, external API access, and session memory management. While prior research has examined various threats, the risk of systematic data exfiltration by backdoored...

Claude SDK For Python: Memory Tool Path Validation Race Condition Allows Sandbox Escape

The async local filesystem memory tool in the Anthropic Python SDK validated that model-supplied paths resolved inside the sandboxed memory directory, but then returned the unresolved path for subsequent file operations. A local attacker able to write to the memory directory could retarget a...

CVE-2026-34451

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...

CVE-2026-34452

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...

CVE-2026-34450

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...