arXiv — MATRA Threat Modeling Framework for Agentic AI Systems 2026-05-17 Security / AI CVEs / Research
arXiv — Security Risks in Tool-Enabled AI Agents in Privileged Cloud Environments 2026-05-17 Security / AI CVEs / Research
Cymulate — Prompt Injection Triggers Zero-Click RCE in AI CLI Tools (Cursor, Kiro, Codex, Gemini) 2026-05-17 Security / AI CVEs / Research
EU CRA — Vulnerability Reporting Obligations for AI Vendors Begin September 2026 2026-05-17 Security / AI CVEs / Research
Forcepoint — 10 In-the-Wild Indirect Prompt Injection Payloads Targeting AI Agents 2026-05-17 Security / AI CVEs / Research
MCP Database Flaws — Apache Doris, Pinot and Alibaba RDS Vulnerabilities 2026-05-17 Security / AI CVEs / Research
Hunt.io — TeamPCP FIRESCALE Malware Uses GitHub Dead-Drop for C2 Resilience 2026-05-17 Security / AI CVEs / Research
VectorSmuggle — Steganographic Data Exfiltration Through AI Embeddings 2026-05-17 Security / AI CVEs / Research
arXiv — Re-Triggering Safeguards: Embedding Disruption for Jailbreak Detection 2026-05-16 Security / AI CVEs / Research
Google GTIG — PROMPTSPY Autonomous AI Malware Interprets Systems and Generates Commands 2026-05-16 Security / AI CVEs / Research
HackerOne — Prompt Injection Reports Surge 540% Year-over-Year 2026-05-16 Security / AI CVEs / Research
Next.js CVE-2026-44578 — WebSocket SSRF Threatens AI-Generated Web Apps 2026-05-16 Security / AI CVEs / Research
NVIDIA Red Team — Indirect AGENTS.md Injection via Malicious Dependencies 2026-05-16 Security / AI CVEs / Research
TeamPCP — Hackers Offer Stolen Mistral AI Source Code for $25K on BreachForums 2026-05-16 Security / AI CVEs / Research
TeamPCP — Shai-Hulud Worm Source Code Open-Sourced, BreachForums Contest Launched 2026-05-16 Security / AI CVEs / Research
UK AISI — New Mythos Checkpoint Completes Previously Unsolved Cyber Ranges 2026-05-16 Security / AI CVEs / Research
Anthropic — Glasswing Red Team Blog Discloses Thousands of AI-Found Zero-Days Across Major OS and Browsers 2026-05-15 Security / AI CVEs / Research