Posts

Pluto Security — CVE-2026-4372 Hugging Face Transformers Config Injection RCE

A critical RCE flaw in Hugging Face Transformers lets attackers execute code via a poisoned config.json field, bypassing trust_remote_code=False.

Meta AI Chatbot — 20,000+ Instagram Account Takeovers

Microsoft — Seven New AI Agent Attack Vectors in Failure Taxonomy

Microsoft expanded its AI agent failure taxonomy with seven new critical attack vectors, including MCP/plugin abuse, session context contamination, and gradual reasoning bias injection.

OWASP — Agentic AI Security Maturity Framework launched at Infosecurity Europe 2026

OWASP released a risk-quadrant maturity framework for agentic AI, mapping autonomy against governance to flag high-risk deployments as red cells.

Varonis — OpenClaw Agent Phishing Simulation Exposes Cloud Credentials

Varonis Threat Labs tricked an OpenClaw email agent into forwarding AWS IAM keys, database passwords, and CRM exports to an attacker after receiving a convincing phishing email.

Anthropic — Claude Fable 5 and Mythos 5 Launch with Cybersecurity Guardrails

Anthropic splits its Mythos-class model into two tiers: unrestricted Mythos 5 for vetted cyber professionals and safeguarded Fable 5 that falls back to Opus 4.8 for cybersecurity queries.

arXiv — Poise: Undetectable Skill Injection on LLM Agents

Poise achieves 89.3% attack success rate on LLM agent skills by exploiting position-aware injection — and bypasses current scanner defenses through false-positive blending.

CISA Adds CVE-2026-42271 to KEV — LiteLLM Active Exploitation Confirmed

CISA added CVE-2026-42271 (LiteLLM command injection) to its Known Exploited Vulnerabilities catalog on June 8, 2026 — confirming active exploitation of the chained BadHost RCE chain against AI serving infrastructure.

CleverHans Lab — AI Worm Spreads Across 27 Nodes Using Free Local LLMs

University of Toronto researchers built an AI-powered worm using free local LLMs that self-replicated across 27 of 33 systems in a simulated enterprise network over five generations.

The Register — Miasma Supply-Chain Attack Toolkit Open-Sourced on GitHub

Microsoft Patch Tuesday June 2026 — Copilot CVEs + AI Component Flaws

Check Point — IKEv1 VPN Auth Bypass (CVE-2026-50751) Exploited by Qilin Ransomware

Check Point discloses CVE-2026-50751, a critical IKEv1 authentication bypass actively exploited since May by Qilin ransomware; CISA adds it to the KEV catalog.

Claude Code MCP Token Theft — npm Package MITM

Cymulate — InversePrompt Bypasses Claude Code Path Restrictions & Command Injection (CVE-2025-54794, CVE-2025-54795)

Docker — AI Coding Agent Horror Stories: Filesystem Destruction Risk

Docker publishes real-world case studies of AI agents destroying user data outside sandboxed workspaces, including a Claude Cowork incident that deleted 15,000+ photos.

Google Sites — Fake Claude Code and Codex Installer Phishing Campaign

Threat actors use Google Sites-hosted fake Claude Code and OpenAI Codex installer pages to trick developers into running credential-stealing commands.

depthfirst AI Agent Finds 21 FFmpeg Zero-Days

An autonomous AI agent found 21 previously unknown vulnerabilities in FFmpeg, including bugs latent for up to 23 years, at a cost of roughly $1,000 per scan run.

LiteLLM PyPI Supply-Chain Attack — Malicious Versions 1.82.7 & 1.82.8 Published Directly to PyPI

NVIDIA — SkillSpector Open-Source Scanner for AI Agent Skills

NVIDIA released SkillSpector, an open-source security scanner that detects 64 vulnerability patterns across 16 categories in AI agent skills before installation.

CVE-2026-6942 — radare2-mcp Command Injection

A critical OS command injection vulnerability (CVSS 9.8) in radare2-mcp allows unauthenticated remote attackers to execute arbitrary commands via the JSON-RPC interface.