Posts

High-signal AI/security/automation notes.

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

arXiv — Prompt Injection 2.0: hybrid AI threats

2026-03-03 Research

BlacksmithAI — Multi-agent penetration testing framework

2026-03-03 Security

NVD — MCP TypeScript SDK cross-client data leak (CVE-2026-25536)

2026-03-03 AI CVEs

GitLab Advisory — MCPJam Inspector RCE (CVE-2026-23744)

2026-03-03 AI CVEs

Oasis Security — ClawJacked OpenClaw WebSocket takeover

2026-03-03 Security

arXiv — Jailbreaking LLMs & VLMs: mechanisms and unified defenses

2026-03-02 Research

ServiceNow — AI Platform RCE (CVE-2026-0542)

2026-03-02 AI CVEs

GitHub Advisory — vLLM trust_remote_code bypass RCE

2026-03-02 AI CVEs

GitLab Advisory — MCP Go SDK case-folding bug (CVE-2026-27896)

2026-03-01 AI CVEs

GitLab Advisory — mcp-server-git path traversal (CVE-2026-27735)

2026-03-01 AI CVEs

MIT AI Agent Index — transparency gaps in agent safety reporting

2026-03-01 Security

Orca Security — RoguePilot GitHub Copilot prompt injection

2026-03-01 Security

arXiv — Analysis of LLMs against prompt injection and jailbreak attacks

2026-02-28 Research

Endor Labs — Six OpenClaw vulnerabilities via AI SAST

2026-02-28 AI CVEs

SD Times — MCP privacy and security gaps

2026-02-28 Security

arXiv — Agentic AI as a cybersecurity attack surface

2026-02-27 Research

arXiv — Silent Egress: implicit prompt injection makes LLM agents leak without a trace

2026-02-27 Research

IBM — X-Force Threat Intelligence Index 2026

2026-02-27 Security

Provos.org — IronCurtain agent sandbox architecture

2026-02-27 Security

OpenReview — Jailbreaking the Matrix with Nullspace Steering

2026-02-27 Research