Latest AI signal

High-signal AI security, infrastructure, and research — short notes with primary sources.

Browse all posts Browse categories

Filter: All Security / AI CVEs / Research (156)Tool Comparisons (2)Research (151)Security / AI CVEs / Research (556)

Latest

AI Bug Hunting Drives Record CVE Spike — 1,500 High-Severity Flaws in June 2026

2026-07-07 Security / AI CVEs / Research

FatFs: LLM-Assisted Fuzzing Finds 7 CVEs in Embedded Firmware

2026-07-07 Security / AI CVEs / Research

NVIDIA Releases SkillSpector — Open-Source Scanner for AI Agent Skills

2026-07-07 Security / AI CVEs / Research

TrendAI Audit Finds 4,982 Security Flaws Across 2,259 Public MCP Servers

2026-07-07 Security / AI CVEs / Research

Vercel Breach: Shadow AI Tool Becomes Identity-Based Supply Chain Pivot

2026-07-07 Security / AI CVEs / Research

Adversa AI — 27 Agentic AI Security Resources for July 2026

2026-07-06 Security

Check Point — Critical Vulnerability Exposures Double in 2026, AI-Driven Triage Urgent

2026-07-06 Security

China — AI Companion Regulation Forces ByteDance and Alibaba to Kill Agent Features

2026-07-06 Security / AI CVEs / Research

CMU — FLARE-AI Open-Source Platform for Cross-Platform AI Vulnerability Reporting

2026-07-06 Security / AI CVEs / Research

Microsoft — CVE-2026-41106 Copilot Cross-Tenant Privilege Escalation

2026-07-06 Security / AI CVEs / Research

IMA Attack — Collaborative-Adversarial Jailbreak Hits 89% Against Multi-Agent Systems

2026-07-06 Research

Tencent AI-Infra-Guard — Multi-Layer Agent Red Teaming Framework

2026-07-05 Security / AI CVEs / Research

arXiv — SkillCloak Bypasses 90%+ of Agent Skill Scanners With Payload-Preserving Evasion

2026-07-05 Security / AI CVEs / Research

AvePoint: 88% of Organizations Report AI Agent Security Breaches as Visibility Gaps Triple

2026-07-05 Security / AI CVEs / Research

T3MP3ST — Open-Source Framework Turns AI Coding Agents Into Autonomous Red Teamers

2026-07-05 Security / AI CVEs / Research

CVE-2026-52830 — fast-mcp-telegram Path Traversal Bypasses Session Protection

2026-07-04 Security / AI CVEs / Research

DataDome — AI Agent Identity Crisis Drives H1 2026 Threat Landscape

2026-07-04 Security / AI CVEs / Research

ICML 2026 — Prompt Injection as Role Confusion and CoT Forgery

2026-07-04 Security / AI CVEs / Research

LiteLLM Three-CVE RCE Chain — Default User to Full AI Gateway Compromise in Two Seconds

2026-07-04 Security / AI CVEs / Research

Unit 42 — Malicious OpenClaw Skills on ClawHub Delivered Infostealers and Crypto Fraud

2026-07-04 Security / AI CVEs / Research

See full feed →