Secure Shell
PulseAugur coverage of Secure Shell — every cluster mentioning Secure Shell across labs, papers, and developer communities, ranked by signal.
20 day(s) with sentiment data
-
New OpenSSH-based SSH client Rasshua released on F-Droid
A new SSH client named Rasshua has been released on F-Droid, offering an alternative to existing options. This client is built upon the OpenSSH suite, providing core functionalities like SSH, SFTP, and SCP. The project …
-
LLM-driven honeypots use narrative deception to trap attackers
A new research paper explores the effectiveness of narrative deception in cybersecurity, specifically using Large Language Models (LLMs) to create more convincing honeypots. The study proposes a strategy where defenders…
-
AgentParley addresses user objections on cost, security, and functionality
AgentParley, a hosted crew of specialist AI agents, addresses common objections from potential users. The service differentiates itself from self-hosted solutions like OpenClaw by handling operational costs and maintena…
-
ShellHub v0.30.2 and crowdsec-web-ui 2026.11.8 released with performance and stability improvements
ShellHub has released version v0.30.2, which promises faster Secure Shell (SSH) sessions and includes a fix for an agent crash. Additionally, the crowdsec-web-ui project has seen an update to version 2026.11.8, addressi…
-
AI agent rewrites instructions to steal credentials after approval
An MCP server, after initially responding correctly to routine requests, altered its own instructions to search for SSH keys and cloud credentials. This malicious shift occurred post-approval, highlighting the critical …
-
Researcher builds tool to detect AI tool poisoning attacks
A security researcher has developed a tool called AgentCheck to detect "tool poisoning" attacks against AI models. These attacks involve malicious servers providing deceptive tool descriptions that trick AI agents into …
-
OpenClaw uses SSH tunnels for dashboard access and keyless remote command execution
This guide explains how to use OpenClaw, an open-source agent gateway, with SSH for secure access. It details two primary methods: accessing the OpenClaw dashboard via an SSH tunnel and enabling the OpenClaw agent to ex…
-
Claude Code leaks thousands of secrets to public GitHub repositories
Security researchers at Apiiro have discovered that Anthropic's Claude Code assistant is inadvertently leaking sensitive information, including API tokens and database passwords, onto public GitHub repositories. This oc…
-
Student builds multi-platform SSH client with Anthropic's Claude Code
A cybersecurity student developed ZestSSH, a comprehensive SSH client for multiple platforms, leveraging Anthropic's Claude Code for feature specification, UI mockups, and security design. The app offers end-to-end encr…
-
Researchers achieve root access by escaping Firecracker microVM
Researchers have detailed a method to escape Amazon's Firecracker microVM, a security technology designed to isolate untrusted code. The PwnEscape Part 2 blog post explains how they achieved code execution as root on th…
-
Claude Dispatch extension vulnerability allows OS command execution
A security vulnerability has been discovered in Claude Dispatch, an extension that allows Claude Desktop to execute commands on a user's operating system. Researchers from Forever Security demonstrated that a malicious …
-
LLM agent audit tool reveals security risks in Claude Code and Codex sessions
An engineer developed a tool called agentblast to audit the security risks associated with LLM agents, particularly those using Claude Code and Codex. The audit of 153 local sessions revealed significant security vulner…
-
Hermes Agent SSH access enhanced with Termalin for improved security
This article details how the Hermes Agent can be configured to access remote servers via SSH, highlighting its current limitations and proposing an alternative solution using Termalin. The default SSH backend requires a…
-
New tools grant AI agents controlled remote access, bypassing full SSH
Two new tools, Buckle and sshboard, offer AI agents controlled access to remote machines without granting full SSH privileges. Buckle acts as an HTTP-based execution harness, allowing agents to perform specific tasks li…
-
Developer Secures Local LLM Relay Exposed via Default Key
A developer discovered security vulnerabilities in a local LLM relay setup, which was inadvertently exposed on all network interfaces with a default placeholder key. The relay was intended to provide access to multiple …
-
Trojanized Claude Code extension found on Cursor marketplace
A malicious Claude Code extension, not developed by Anthropic, was available on the Cursor marketplace for approximately 11 hours on October 29th. This trojanized extension, versions 2.1.312 and 2.1.313, planted an "svc…
-
Malicious Claude Code extension with SSH backdoor tracked by Microsoft
A malicious browser extension, deceptively branded as "Claude Code," has been identified that installs a persistent SSH backdoor. This tool exploits the trust associated with legitimate AI coding assistants to gain dura…
-
Malicious Claude Code extension distributed via Cursor IDE marketplace
A malicious version of the Claude Code extension was distributed through the Cursor IDE's marketplace on October 29, 2026. This tampered extension, versions 2.1.312 and 2.1.313, was available for approximately eleven ho…
-
Neovim plugin secures AI coding agents against SSH key access
A new Neovim plugin has been developed using Rust to address security concerns with AI coding agents. This plugin aims to prevent AI agents from accessing sensitive user data, such as SSH keys, by ensuring they are not …
-
Malicious Claude Code extension in Cursor marketplace attempted SSH backdoor
A malicious version of the Anthropic.claude-code extension (2.1.313) was distributed through the Cursor VS Code extension Marketplace between October 29, 2026, 2:27 AM PT and 1:35 PM PT. This unauthorized version attemp…