Tag: malicious

AI can help attackers generate malware, create malicious payloads, bypass simple security checks, and convert vague malicious intent into functional code. The post The Zero-Knowledge Threat Actor and the End of Responsible Disclosure appeared first on SecurityWeek.

Malicious repositories and disguised symlinks can trick AI coding agents into silently installing attacker-controlled MCP servers capable of stealing secrets, compromising CI pipelines, and deploying malicious code. The post ‘SymJack’ Attack Turns AI Coding Agents Into Supply Chain Attack Delivery Systems appeared first on SecurityWeek.

More than 500 packages were pushed during the attack, but the target appears to have been RubyGems itself rather than users. The post Hundreds of Malicious Packages Force RubyGems to Suspend Registrations appeared first on SecurityWeek.

Over 400 malicious versions of 170 packages were published as part of the new Mini Shai-Hulud campaign. The post TanStack, Mistral AI, UiPath Hit in Fresh Supply Chain Attack appeared first on SecurityWeek.

A malicious version of the plugin was published to the Jenkins Marketplace late last week. The post Checkmarx Jenkins AST Plugin Compromised in Supply Chain Attack appeared first on SecurityWeek.

A malicious Hugging Face repository that reached the platform’s trending list impersonated OpenAI’s „Privacy Filter“ project to deliver information-stealing malware to Windows users. […]

Malicious repositories can trigger code execution in Claude Code, Cursor CLI, Gemini CLI, and CoPilot CLI with minimal or no user interaction, thanks to skimpy warning dialogs.

The malicious emails claim to contain a conduct report and lure victims to a Microsoft phishing website that leverages AitM. The post Microsoft Warns of Sophisticated Phishing Campaign Targeting US Organizations appeared first on SecurityWeek.