Gartner — Agentic AI Will Trigger Security Incidents at Scale 2026-04-21 Security / AI CVEs / Research
LMDeploy CVE-2026-33626 — SSRF in LLM Serving Toolkit Vision Module 2026-04-21 Security / AI CVEs / Research
LogJack — Indirect Prompt Injection Through Cloud Logs Against LLM Debugging Agents 2026-04-21 Security / AI CVEs / Research
Postiz — CVE-2026-40487 Stored XSS via File Upload Validation Bypass 2026-04-21 Security / AI CVEs / Research
Prompt Injection as Role Confusion — CoT Forgery Achieves 60% ASR on Frontier Models 2026-04-21 Security / AI CVEs / Research
UK AI Safety Institute — LLM Jailbreaks and Cyber Evaluations 2026-04-21 Security / AI CVEs / Research
Unit42 — Frontier AI Models Autonomously Discovering Vulnerabilities 2026-04-21 Security / AI CVEs / Research
VulnCheck — Project Glasswing: Only 1 Confirmed CVE Despite Anthropic Mythos Hype 2026-04-21 Security / AI CVEs / Research
Suzu Labs — Dark web operators pivot to frontier LLMs for offensive cyber 2026-04-20 Security / AI CVEs / Research
Georgia Tech Vibe Security Radar — 74 CVEs Traced to AI Coding Tools 2026-04-20 Security / AI CVEs / Research
GreyNoise — 91K attack sessions reveal active targeting of exposed LLM infrastructure 2026-04-19 Security / AI CVEs / Research
iProov Threat Intelligence Report — 1,151% Surge in iOS Deepfake Injection Attacks 2026-04-19 Security / AI CVEs / Research
Microsoft — Excel XSS chains to Copilot Agent for clickless data exfiltration (CVE-2026-26144) 2026-04-19 Security / AI CVEs / Research