8 articles with this tag
GhostSplice: Multi-Tool Payload Assembly in MCP Agents
Inside GhostSplice (August 2026): how malicious MCP tools split instructions across turns to bypass single-prompt guardrails and exfiltrate developer secrets.
The CTF Escape Horizon: AI Agent Model Breakouts Explained
An analysis of the July 2026 OpenAI and Anthropic sandbox escapes, zero-day Artifactory exploits, misconfigured evals, and microVM isolation.
Inside JADEPUFFER: Anatomy of the First Autonomous AI Ransomware
Analyzing the JADEPUFFER campaign, the first fully autonomous AI ransomware. We dissect its exploit chain, error debugging, and self-narrating payloads.
The AI Spam That Almost Broke the Linux Kernel
Discover how the Linux Kernel community is fighting AI-generated bug report spam by enforcing DCO human-liability sign-offs and Assisted-by metadata tags.
Hardening the Model Context Protocol: Securing Enterprise Agents
Learn how to secure the Model Context Protocol (MCP) in enterprise environments. Discover SSE gateway patterns, transport security, and tool access filters.
The Verification Bottleneck: Why AI Agents Can't Grade Their Own Code
With 36.8% of AI agent skills containing security flaws, learn why independent verification layers like Google ADK are critical to securing agent runtimes.
NGINX Rift: How Autonomous AI Found an 18-Year-Old RCE Bug
An 18-year-old heap buffer overflow in NGINX was found by an autonomous AI agent in 6 hours. We analyze NGINX's script engine memory layout and exploit chain.
16 Million Stolen Queries: Inside the Anthropic Distillation Attacks and the Hydra Clusters
How DeepSeek, Moonshot AI, and MiniMax used 24,000 fraudulent accounts to distill Claude’s capabilities — and why your API security might be the next target.