Wiz — Red Agent, AI-BOM, and Wiz Code Expand AI Application Security Platform 2026-04-30 Security / AI CVEs / Research
arXiv — LLMs Fail at Open-Ended Threat Hunting (3.8% Best Score) 2026-04-29 Research / AI Security Benchmarks
Lufsec — Model Context Protocol: 4 Trust Boundaries Attackers Are Exploiting 2026-04-29 Security / AI CVEs / Research
DPRK PromptMink — Claude Opus Used to Insert Malicious npm Dependency 2026-04-29 Security / AI CVEs / Research
Hugging Face LeRobot — Critical Pickle Deserialization RCE (CVE-2026-25874) 2026-04-29 Security / AI CVEs / Research
Pipecat Voice Agent Framework — Pickle Deserialization RCE (CVE-2025-62373) 2026-04-29 Security / AI CVEs / Research
T-MAP — Red-Teaming LLM Agents with Trajectory-aware Evolutionary Search 2026-04-29 Research / arXiv / SoK
TeamPCP — Claude Code Used to Publish Malicious SAP CAP npm Packages 2026-04-29 Security / AI CVEs / Research
Cisco — Claude Code memory poisoning enables persistent agent compromise 2026-04-28 Security / AI CVEs / Research
Cursor AI Agent Deletes PocketOS Production Database in 9 Seconds 2026-04-28 Security / AI CVEs / Research
vanna-ai — CVE-2026-6977 Improper Authorization in Legacy Flask API 2026-04-28 Security / AI CVEs / Research
Bitwarden CLI Compromised — Shai-Hulud Campaign Targets AI Coding Assistants 2026-04-27 Security / AI CVEs / Research
Foresiet — Meta AI Agent Hallucinates Permissions, Exposes Internal Data 2026-04-27 Security / AI CVEs / Research
Google — 32% Rise in Indirect Prompt Injection Attacks Found Across Public Web 2026-04-27 Security / AI CVEs / Research
Mozilla — 271 Vulnerabilities Found in Firefox 150 by Claude Mythos Preview 2026-04-27 Security / AI CVEs / Research
OpenAI GPT-5.5 Launches With Agentic Safeguard Delays and Bio Bug Bounty 2026-04-27 Security / AI CVEs / Research
OpenClaw — Three Flaws Enable Policy Bypass and API Credential Theft 2026-04-27 Security / AI CVEs / Research