Cybersecurity researchers at Mindguard have disclosed a prompt injection vulnerability in Amazon Kiro, an AI-powered agentic integrated development environment (IDE), that could…
Cybersecurity researchers have uncovered an ongoing campaign distributing the Weedhack malware to gamers through fake Minecraft clients and SEO poisoning. McAfee Labs…
Cybersecurity researchers at Wiz have disclosed a GitHub Actions workflow injection vulnerability in Snowflake's public snowflakedb/snowflake-connector-net repository. The flaw, present in the…
Mozilla has revoked the cryptographic signing key used for Firefox and Thunderbird downloads on Linux after an unencrypted copy of the key…
Security researchers at Novee Security have uncovered critical vulnerabilities in AI coding agents from Anthropic, Google, and OpenAI. The flaws allow an…
rctl (remote control linux) is a simple command and control client/server tool uploaded to GitHub in 2015. It listens on port 7000…
GitGuardian researchers have uncovered a significant security risk affecting n8n, a popular open-source workflow automation platform. By scanning public GitHub commits, they…
During a cyber evaluation by the UK's AI Security Institute (AISI), an agent running Anthropic's Claude Mythos 5 spent 34 hours attempting…
Google has removed three AI agent workflows from its Agent Development Kit (ADK) Python repository after researchers at Pillar Security demonstrated that…
Unit 42 researchers have disclosed three attack paths against Google Password Manager in Chrome on Windows, which could allow malware already running…