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 //
PLUGIN-SECURITY

Plugin-Security

3 reports
All LLM Security Industry News Agentic AI Research Supply Chain Prompt Injection Regulatory Adversarial ML Jailbreaks Model Theft Data Poisoning
Prompt Injection Achieves Remote Code Execution in Semantic Kernel Agent Framework
ATLAS OWASP CRITICAL Active exploitation · Immediate action required Microsoft Security Blog ▲ 9.2

Prompt Injection Achieves Remote Code Execution in Semantic Kernel Agent Framework

Microsoft's Defender Security Research Team disclosed two CVEs in Semantic Kernel — a widely-used AI agent orchestration framework — demonstrating how prompt injection can escalate to remote code …

AML.T0051 - LLM Prompt Injection AML.T0047 - ML-Enabled Product or Service AML.T0043 - Craft Adversarial Data
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