Attackers can inject indirect prompts in normal-looking repositories to trick Claude Code into spawning a reverse shell.

A reverse shell makes the target machine initiate the connection back to the attacker, bypassing firewalls that only filter ...

Mozilla’s 0din team showed how a Claude Code malware GitHub repo attack could use a clean-looking repository to open a ...

An agentic coding tool tasked with cloning and setting up a seemingly benign GitHub repository could execute a malicious ...

SentinelOne details Gaslight, a Rust-based macOS implant linked to North Korea-aligned actors that uses prompt injection to ...

SentinelOne says macOS.Gaslight uses prompt injection to mislead AI-based malware analysis, steal data, and use Telegram for ...

Three levels of indirection, all with seemingly innocuous steps, will catch a bot off-guard.

In the previous article, I demonstrated how a reverse shell can be executed from the attacker's perspective (Red Team). In this article, I want to look at the same attack from the server's point of ...

A China-nexus cyber espionage group has been observed deploying a BSD variant of a known backdoor called BRICKSTORM, as well as two other malware families codenamed PLENET (aka GRIMBOLT) and AGENTPSD ...

The generated prompts are designed to resemble powerline, but otherwise this project has no relation to powerline. This script uses ANSI color codes to display colors in a terminal. These are ...

Researchers warn malicious GitHub repositories can trick AI coding agents into running hidden malware through trusted setup steps, risking developer systems and credentials. Google - Gemini A newly ...