GitHub Breach — Poisoned VS Code Extension Exfiltrates 3,800 Internal Repos 2026-05-20 Security / AI CVEs / Research
Mini Shai-Hulud — Malware Persists via Claude Code Hooks and VS Code Auto-run Tasks 2026-05-20 Security / AI CVEs / Research
SentinelOne — Prompt for Agentic AI Security: MCP Discovery and Runtime Governance 2026-05-20 Security / AI CVEs / Research
Sysdig: Runtime Security Is the Missing Layer in Agentic AI Tooling 2026-05-20 Security / AI CVEs / Research
Anthropic — Mythos Glasswing Expands: Verizon Joins, Findings-Sharing Policy Revised 2026-05-19 Security / AI CVEs / Research
Discourse — CVE-2026-32244 Cached AI Summaries Leak Removed Content 2026-05-19 Security / AI CVEs / Research
Forcepoint — TeamPCP Turns LiteLLM into a Credential Stealer 2026-05-19 Security / AI CVEs / Research
Lasso Security — Open-Source Claude Code Prompt Injection Defender 2026-05-19 Security / AI CVEs / Research
n8n — Five Critical CVEs Including Prototype Pollution RCE in AI Workflow Platform 2026-05-19 Security / AI CVEs / Research
NVIDIA Vera CPU — First Deliveries to Anthropic, OpenAI, Oracle for Agentic AI Infrastructure 2026-05-19 Security / AI CVEs / Research
OX Security — First Shai-Hulud Clones Hit npm with DDoS Botnet 2026-05-19 Security / AI CVEs / Research
Truffle Security — Claude Coding Agent Autonomously Exploited SQL Injection Across 30 Companies 2026-05-19 Security / AI CVEs / Research
Wiz — TeamPCP Hits @antv npm Namespace, GitHub Actions, and VSCode 2026-05-19 Security / AI CVEs / Research
CrossMPI — Image-Only Prompt Injection Attacks Multimodal AI Models 2026-05-18 Security / AI CVEs / Research
ExploitBench — AI Agents Achieve Arbitrary Code Execution on V8 2026-05-18 Security / AI CVEs / Research
Linus Torvalds — AI Bug Reports Overwhelm Linux Security Mailing List 2026-05-18 Security / AI CVEs / Research
MCPSafe — 7 Coordinated Disclosures After Scanning 50+ MCP Servers 2026-05-18 Security / AI CVEs / Research
OpenClaw Five-Point Security Plan — fs-safe, Proxyline, ClawHub Ratings 2026-05-18 Security / AI CVEs / Research
Pwn2Own Berlin 2026 — OpenAI Codex Exploited, $1.29M in 47 Zero-Days 2026-05-18 Security / AI CVEs / Research