Microsoft Semantic Kernel CVE-2026-26030/25592 — Prompt Injection to RCE 2026-05-25 Security / AI CVEs / Research
NSA Releases MCP Security Design Considerations for AI-Driven Automation 2026-05-25 Security / AI CVEs / Research
Open-Source LLMs Vulnerable to Long Reasoning Multi-Turn Jailbreaks 2026-05-25 Security / AI CVEs / Research
Cybersecurity Insiders — Three Prompt Injection Detection Blind Spots 2026-05-25 Security / AI CVEs / Research
TrapDoor Supply Chain — .cursorrules and CLAUDE.md Hijack AI Assistants 2026-05-25 Security / AI CVEs / Research
1Password + OpenAI — Just-in-Time Credentials for Codex Agents 2026-05-24 Security / AI CVEs / Research
Adaptive Security — 80% of employees use unapproved AI tools, 12% of companies govern them 2026-05-24 Security / AI CVEs / Research
arXiv — HBHC Protocol Solves Zombie Agent Credential Revocation 2026-05-24 Security / AI CVEs / Research
arXiv OverEager — coding agents exceed authorized scope on benign tasks 2026-05-24 Security / AI CVEs / Research
Aikido Security — Laravel-Lang supply chain delivers cross-platform credential stealer 2026-05-24 Security / AI CVEs / Research
LMDeploy CVE-2026-46517 — hardcoded trust_remote_code bypasses HF default-secure 2026-05-24 Security / AI CVEs / Research
MDPI — attack surfaces of malicious remote MCP servers across LLM platforms 2026-05-24 Security / AI CVEs / Research
NVIDIA OpenShell — open-source secure sandboxed runtime for AI agents 2026-05-24 Security / AI CVEs / Research
arXiv — ASPI Shows Clarification-Seeking Amplifies Prompt Injection in LLM Agents 2026-05-23 Security / AI CVEs / Research
arXiv — Domain-Camouflaged Prompt Injections Evade LLM Injection Detectors 2026-05-23 Security / AI CVEs / Research
CISA Adds Langflow Origin Validation Flaw to KEV — Active Exploitation Confirmed 2026-05-23 Security / AI CVEs / Research
Google Threat Intel — LLM-Generated Morphing Malware and Automated Vulnerability Discovery 2026-05-23 Security / AI CVEs / Research
TeamPCP — 20-Wave Supply-Chain Campaign Hits 500+ Tools, GitHub 2026-05-23 Security / AI CVEs / Research