LIVE FEED
FIRST LOOK Anthropic and OpenAI Open Doors to Embedded Safety Evaluators // HIGH OpenAI Reports Six Cases of Unsafe AI Model Behavior // HIGH BragJack Attack Hijacks Browser AI Agents to Steal Data // CRITICAL Agentic AI Causes First Autonomous Data Breach in Spain // MEDIUM Autonomous AI Agents Abuse Internet Access and Email Systems // FIRST LOOK Anthropic Co-Founder Calls for Mandatory AI Kill Switch Oversight // HIGH CVE-2026-39987: Marimo RCE Exploited to Breach SSH Bastion // HIGH PhantomRaven: LLM-Generated Info Stealer Built for Bug Bounty // FIRST LOOK AIUC Launches AIUC-1 Agent Certification Standard for Enterprises // CRITICAL Anthropic Exposes 200M-Exchange Model Distillation Attacks //
INFORMATION-STEALER

Information-Stealer

3 reports
All LLM Security Agentic AI Industry News Research Supply Chain First Look: Security Prompt Injection Regulatory Adversarial ML Jailbreaks Model Theft Data Poisoning Deep Signal Intelligence Report AI Governance AI Security AI Security Tools Identity & Access Management Monthly Review Security Operations
PhantomRaven: LLM-Generated Info Stealer Built for Bug Bounty

PhantomRaven: LLM-Generated Info Stealer Built for Bug Bounty

ATLAS OWASP HIGH Significant risk · Prioritise patching ▲ 8.2 CrowdStrike Blog

CrowdStrike has identified PhantomRaven, an information stealer developed using large language models and framed under the guise of bug bounty hunting, highlighting the growing abuse of AI code generation for malware development. The case demonstrates how LLMs can be leveraged to lower the technical barrier for building functional credential-stealing tools. This development signals a significant shift in the threat landscape where AI-assisted malware authorship is becoming operationally viable for a wider range of actors.

mouse5212-super-formatter npm Malware Steals Claude Files

mouse5212-super-formatter npm Malware Steals Claude Files

ATLAS OWASP HIGH Significant risk · Prioritise patching ▲ 8.2 The Hacker News

A malicious npm package named 'mouse5212-super-formatter' was discovered exfiltrating files from Anthropic's Claude AI user directory by authenticating to a threat actor-controlled GitHub repository. The package disguised itself as a legitimate archive utility while silently uploading all local workspace files during the postinstall phase. Notably, the attacker's poor operational security — including a leaked GitHub token — suggests AI-generated malware with minimal human oversight, pointing to a growing trend of low-skill threat actors leveraging AI to produce supply chain malware.

PyTorch Lightning Package Backdoor Steals Developer Credentials

PyTorch Lightning Package Backdoor Steals Developer Credentials

ATLAS OWASP HIGH Significant risk · Prioritise patching ▲ 8.5 BleepingComputer

A malicious version of PyTorch Lightning (v2.6.3) was published to PyPI, embedding a hidden execution chain that silently downloads a JavaScript runtime and executes a heavily obfuscated credential-stealing payload dubbed 'ShaiWorm'. The attack targeted AI/ML developers who use this popular deep learning framework, exposing cloud credentials, API keys, browser-stored secrets, and GitHub tokens. The package has since been reverted to a safe version, but any developer who imported the compromised version should rotate all secrets immediately.

◉ AI THREAT BRIEFING

Stay ahead of the threat.

Twice-weekly digest of critical AI security developments — every story mapped to MITRE ATLAS and OWASP LLM Top 10. Free.

No spam. Unsubscribe anytime.