Latest AI signal

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

Browse all posts Browse categories

Filter: All AI CVEs (44)Tool Comparisons (2)Research (38)Security (107)

Latest

arXiv — Contextualized privacy defense for LLM agents

2026-03-08 Research

arXiv — Image-based prompt injection against multimodal LLMs

2026-03-08 Research

GitHub Advisory — Copilot CLI shell expansion RCE (CVE-2026-29783)

2026-03-07 AI CVEs

Huntress — Fake OpenClaw installers spread GhostSocks

2026-03-07 Security

GitLab Advisory — mcp-memory-service info disclosure (CVE-2026-29787)

2026-03-07 AI CVEs

Noma Security — ContextCrush in Context7 MCP server

2026-03-07 Security

GitHub Advisory — Agentgateway MCP→OpenAPI parameter injection (CVE-2026-29791)

2026-03-06 AI CVEs

AI Agent Security Threat Model 2026

2026-03-06 Security

Check Point Research — Claude Code project-file RCE & key exfil

2026-03-06 Security

Securing MCP and Agent Tool Supply Chains

2026-03-06 Security

Microsoft Security Blog — malicious AI assistant extensions harvest LLM chat histories

2026-03-06 Security

Prompt Injection Defense Playbook (2026)

2026-03-06 Security

Cisco Talos — 2025 CVE retrospective (AI-related CVEs double)

2026-03-06 Security

VulnerableMCP — MCP security database for real-world tool flaws

2026-03-06 Security

Arctic Wolf — mcp-atlassian unauth RCE/SSRF (CVE-2026-27825/27826)

2026-03-05 AI CVEs

GitLab Advisory — mcp-nmap-server command injection (CVE-2026-3484)

2026-03-05 AI CVEs

CERT/CC — MS-Agent shell tool command injection (CVE-2026-2256)

2026-03-05 AI CVEs

Unit 42 — Web-based indirect prompt injection observed in the wild

2026-03-05 Security

Techzine — DeepKeep AI Agent Scanner

2026-03-04 Security

GitHub Advisory — Langflow CSV Agent RCE (CVE-2026-27966)

2026-03-04 AI CVEs

See full feed →