Runtime-Exploit-Generation | GRID THE GREY

LIVE THREATS

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 // MEDIUM AI Security M&A Surge: Agentic Identity, LLM Evaluation, and Browser Control Targeted // HIGH Claude Code GitHub Action Leaked CI/CD Secrets via Prompt Injection // HIGH Gartner Flags Deepfakes and Prompt Injection Among Top Attacker Advantages //

1 report

All LLM Security Industry News Agentic AI Research Supply Chain Prompt Injection Regulatory Adversarial ML Jailbreaks Model Theft Data Poisoning

Self-Replicating AI Worm Uses Local LLM to Generate Exploits at Runtime

ATLAS OWASP CRITICAL The Hacker News Jun 10, 2026 ▲ 9.2

Self-Replicating AI Worm Uses Local LLM to Generate Exploits at Runtime

University of Toronto researchers demonstrated a proof-of-concept AI worm that leverages a locally hosted open-weight LLM to autonomously reason through network targets, generate novel exploit chains …

AML.T0047 - ML-Enabled Product or Service AML.T0040 - ML Model Inference API Access AML.T0043 - Craft Adversarial Data