Look, Don't Load: Model Inspection in Unsloth Studio Leads to Critical Arbitrary Code Execution 2026-09-29 75 True Valid, But Never Issued: Session Spoofing and SSRF in Grafana MCP 2026-09-02 85 True A WIF Of Fresh Access: How a GitHub Issue on Gemini-CLI Led to GCP Project Compromise 2026-08-18 75 True Deadbugz: Currently Active MCP Supply-Chain Campaign 2026-08-12 75 True ChainDrop: When Opening a Repository Becomes Execution 2026-08-04 86 True I'll Just Call You: Agent-to-Agent Privilege Boundary Failures in CI/CD on Google's ADK Repository 2026-08-03 75 True Our CTF Mapped an AI Killchain. Days Later, It Appeared in Hugging Face’s Production Environment. 2026-07-30 85 True Our Week of Sandbox Escapes Had Seven Real World Examples. OpenAI Just Added the Eighth 2026-07-23 75 True The Week of Sandbox Escapes Day 4: Git directories do not have to be called .git 2026-07-20 70 True The Week of Sandbox Escapes Day 3: The sandbox let me edit a venv, and something else ran it 2026-07-20 75 True The Week of Sandbox Escapes Day 6: The hook was already in the workspace 2026-07-20 75 True The Week of Sandbox Escapes 2026-07-20 60 True The Week of Sandbox Escapes Day 2: One Docker socket to rule them all: escaping Codex, Cursor, and Gemini CLI's sandboxes 2026-07-20 70 True The Week of Sandbox Escapes Day 5: GitPwned: Allowlist to RCE 2026-07-20 72 True The Week of Sandbox Escapes Day 7: A time bomb in .vscode: bypassing Antigravity's Secure Mode 2026-07-20 70 True The Week of Sandbox Escapes Day 1: Escaping Antigravity's Allow-Default Seatbelt 2026-07-20 70 True The Fable Recall Puts the Spotlight in the Wrong Place 2026-06-14 15 True Your agents answer to Hades: how one commit hijacks 4 AI coding tools 2026-06-10 90 True Your Agent Harness Has More Privilege Than Your Agent 2026-05-26 60 True Untrusted Project-Local Filters in RTK: When Your AI's Eyes Are Someone Else's to Control 2026-05-20 55 True Agentic CI/CD Security: Risks, Attack Vectors, and Controls 2026-05-12 75 True My Agentic Trust Issues: From Prompt Injection to Supply-Chain Compromise on gemini-cli 2026-05-05 90 True Prompt Injection leads to RCE and Sandbox Escape in Antigravity 2026-04-20 75 True The Agent Economy: Who Commands The Fleet 2026-04-08 88 True Zero Click Unauthenticated RCE in n8n: A Contact Form That Executes Shell Commands 2026-03-11 95 True n8n Sandbox Escape: Critical Vulnerabilities in n8n Exposes Hundreds of Thousands of Enterprise AI Systems to Complete Takeover 2026-02-04 92 True Caught in the Wild: Real Attack Traffic Targeting Exposed Clawdbot Gateways 2026-01-29 80 True Operation Bizarre Bazaar: First Attributed LLMjacking Campaign with Commercial Marketplace Monetization 2026-01-28 75 True The Agent Security Paradox: When Trusted Commands in Cursor Become Attack Vectors 2026-01-14 75 True Not All AI BOMs Are Created Equal 2025-12-31 70 True “Ask Gordon, Meet the Attacker” - Prompt Injection in Docker’s Built-in AI Assistant 2025-12-18 80 True The New AI Attack Surface: 3 AI Security Predictions for 2026 2025-12-03 70 True What the Anthropic 'AI Espionage' Disclosure Tells Us About AI Attack Surface Management 2025-11-17 90 True AI Red Teaming Playbook 2025-10-08 30 True Securing Context Engineering 2025-09-10 65 True Anatomy of an Indirect Prompt Injection 2025-08-12 70 True Building Your AI Security Roadmap 2025-07-30 60 True The Security Risks of Model Context Protocol (MCP) 2025-03-24 75 True New Vulnerability in GitHub Copilot and Cursor: How Hackers Can Weaponize Code Agents 2025-03-18 80 True Rethinking AI Security: Beyond the DeepSeek R1 Vulnerability Metrics 2025-02-04 30 True Agentic Use Cases and Challenges for 2025 2025-02-03 10 True The State of Attacks on GenAI: Industry-First Analysis of Real-World Interactions 2024-10-09 75 True Revolutionizing Cybersecurity: The Kill Chain in the Age of AI 2024-07-01 30 True Key Questions for Secure Deployment of Large Language Models 2024-01-24 25 True 
