arXiv: Real-World Prompt Injection Attacks in LLM-Based Resume Screening 2026-05-29 Security / AI CVEs / Research
Flashpoint — Deepfake KYC Bypass Kits Sold as SaaS to Criminals 2026-05-29 Security / AI CVEs / Research
JFrog — 2026 Supply Chain Report: npm Attacks Up 451%, 495 Malicious AI Models 2026-05-29 Security / AI CVEs / Research
jqwik Maintainer Sneaks Data-Nuking Prompt Injection Into AI Coding Agents 2026-05-29 Security / AI CVEs / Research
Langroid CVE-2026-25879 — Prompt-to-SQL Injection Leads to RCE 2026-05-29 Security / AI CVEs / Research
Sysdig: First LLM Agent-Driven Intrusion via Marimo CVE-2026-39987 2026-05-29 Security / AI CVEs / Research
UVCyber MCP Threat Advisory: 40+ CVEs, Tool Poisoning, and the Missing Auth Layer 2026-05-29 Security / AI CVEs / Research
vLLM CVE-2026-4944 — Hardcoded trust_remote_code Bypass Enables RCE 2026-05-29 Security / AI CVEs / Research
Cogent — AI exploit dev shrinks weaponization from 125 days to 12 hours 2026-05-28 Security / AI CVEs / Research
Axis Intelligence — AI Model Vulnerability Tracker: 71% Attack Success Rate Across Six Frontier Models 2026-05-28 Security / AI CVEs / Research
Check Point — AI Attacks Go Mainstream: Single Operator Breached 9 Mexican Agencies Using AI Orchestration 2026-05-28 Security / AI CVEs / Research
GlassWorm — developer-targeting botnet takedown (CrowdStrike, Google) 2026-05-28 Security / AI CVEs / Research
TechRepublic / TechTimes — The AI Agent Governance Gap: 88% of Deployments Already Breached 2026-05-28 Security / AI CVEs / Research
Megalodon — Mass GitHub CI/CD Supply Chain Attack Hits 5,561 Repos 2026-05-28 Security / AI CVEs / Research
Perplexity Bumblebee — Open-Source Scanner for Dev Endpoints and MCP Configs 2026-05-28 Security / AI CVEs / Research
Starlette CVE-2026-48710 "BadHost" — FastAPI AI Infrastructure Exposed 2026-05-28 Security / AI CVEs / Research
Anthropic Claude Code Security-Guidance Plugin — Three-Layer In-Session Vulnerability Detection 2026-05-27 Security / AI CVEs / Research
arXiv — Poisoning the Watchtower: Prompt Injection Against LLM-Augmented SOC Analysts 2026-05-27 Research / AI Security