LIVE THREATS
HIGH Anthropic's Claude Fable 5 Ships Tiered Cyber Safeguards to Limit Offensive AI Uplift // HIGH Rogue AI Agent Infiltrates Fedora Project, Merges Malicious Code via Compromised … // CRITICAL Unauthenticated RCE Flaw in Langflow Actively Exploited, No Patch Available // HIGH AI Email Agent Susceptible to Classic Phishing Tactics, Leaks Credentials and CRM Data // MEDIUM Anthropic Mythos Threatens Bug Bounty Industry with Machine-Speed Vulnerability Discovery // MEDIUM Anthropic's Mythos-Class Claude Fable 5 Ships With Cybersecurity Fallback Guardrails // CRITICAL Claude Mythos Weaponises N-Day Vulnerabilities Into Working Exploits Within Hours // MEDIUM Microsoft Publishes Investigator Playbook for AI Telemetry and Incident Reconstruction // CRITICAL Self-Replicating AI Worm Uses Local LLM to Generate Exploits at Runtime // CRITICAL Miasma Worm Targets AI Coding Agents via Poisoned Microsoft Packages //
HUGGING-FACE

Hugging-Face

3 reports
All LLM Security Industry News Agentic AI Research Supply Chain Prompt Injection Regulatory Adversarial ML Jailbreaks Model Theft Data Poisoning
Typosquatted OpenAI Repo on Hugging Face Delivered Rust Infostealer to 244K Users
ATLAS OWASP CRITICAL Active exploitation · Immediate action required The Hacker News ▲ 8.5

Typosquatted OpenAI Repo on Hugging Face Delivered Rust Infostealer to 244K Users

A malicious Hugging Face repository impersonated OpenAI's legitimate Privacy Filter model, cloning its description verbatim to gain credibility and reach the platform's trending list with 244,000 …

AML.T0010 - ML Supply Chain Compromise AML.T0019 - Publish Poisoned Datasets AML.T0047 - ML-Enabled Product or Service
Hugging Face 'Spaces' now acts as an MCP-App-Store. Anybody thinking on the security consequence?
ATLAS OWASP MEDIUM Moderate risk · Monitor closely Hugging Face Blog ▲ 6.2

Hugging Face 'Spaces' now acts as an MCP-App-Store. Anybody thinking on the security consequence?

Hugging Face's Gradio MCP server integration enables LLMs to connect to thousands of third-party AI tools via Hugging Face Spaces, significantly expanding the attack surface for agentic AI systems. …

AML.T0051 - LLM Prompt Injection AML.T0010 - ML Supply Chain Compromise AML.T0047 - ML-Enabled Product or Service