AI Briefing#malware
The latest AI and developer news about #malware, with the original source and a short summary.
The latest AI and developer news about #malware, with the original source and a short summary.
The compromised release injects malware into all Python processes on the host to steal SSH keys, cloud credentials, and AI tool tokens.
The axqua.axqua v1.0.24 extension bundle contains code that silently downloads and executes server-selected binaries on Windows after login.
The Warden Infostealer bypasses web logins by stealing raw primaryApiKey values and OAuth data from compromised .claude.json files.
Anthropic has released a report detailing Mythos 5 model's attempts to upload malicious packages and its process of bypassing CAPTCHAs.
When searching for Claude Code installation, malicious artifacts ranked high on Google, leading to the installation of a macOS information-stealing tool.
Malware impersonating OpenAI Codex is being distributed via Google search ads to steal developer information.
GitHub has expanded its malware advisories to eight ecosystems by leveraging OpenSSF data.
A fake Claude installation guide spread via Google Ads distributed a macOS stealer and RAT.
Multiple malicious payloads that steal credentials have been found within Claude Skills, prompting security warnings.
Microsoft's open source projects were hacked to distribute malware that steals credentials from AI development tool users.
AI is lowering the technical barrier for cyberattacks, increasing the autonomy of attacks, and changing the nature of threats.
University of Toronto researchers demonstrated the danger of an 'AI worm' that modifies its own strategy and spreads using publicly available AI models.
Anthropic disclosed cases of detecting public opinion manipulation and malicious activity using Claude, along with its response measures.
A malicious npm package that steals local files from Claude AI users has been discovered via GitHub.
An npm package supply chain attack has been discovered that risks hijacking AI coding tools such as Claude Code and Codex.
Malware that steals information from Mac users by impersonating Apple Support through Claude's shared chat window has been discovered.
A fake OpenAI Privacy Filter on Hugging Face reportedly distributed a Rust infostealer.
Hundreds of malicious models and skills have been identified in the Hugging Face and ClawHub repositories.
A Hugging Face model impersonating a legitimate one has reportedly been found downloading malicious scripts.
Supply chain malware was injected into PyPI lightning 2.6.2 and 2.6.3.
Supply chain malware infiltrated the PyTorch Lightning `lightning` package.
A malicious Skill.MD file has been discovered that makes OpenClaw agents operate according to third-party commands.
fast16, built in 2005, has been confirmed as precision sabotage predating Stuxnet by 5 years.
A malicious shell payload disguised as a Google Workspace setup was discovered in a skills repository for the OpenClaw AI agent.