EchoLeak (CVE-2025-32711): The First Zero-Click Production LLM Exfiltration
A single crafted email could exfiltrate data from Microsoft 365 Copilot without a user click. We walk the attack chain, the patch, and the lessons for agent operators.
Deep dives, practical guides, and incident analyses from engineers who build Safeguard. No fluff, no vendor FUD — just what you need to ship secure software.
A single crafted email could exfiltrate data from Microsoft 365 Copilot without a user click. We walk the attack chain, the patch, and the lessons for agent operators.
A repository named Open-OSS/privacy-filter impersonated OpenAI's release, copied its model card verbatim, and shipped a loader.py that pulled an infostealer. It reached #1 trending with ~244,000 downloads before removal.
Cyera disclosed Bleeding Llama in May 2026: a heap out-of-bounds read in Ollama's GGUF loader leaking process memory. We dissect the bug and the exposure across 300,000 Ollama deployments.
MCP servers expose three distinct prompt-injection surfaces — resource contents, tool outputs, and sampling requests — and each one needs its own defense layer. Here is how to think about them together.
Tool-poisoning attacks against Model Context Protocol servers hide adversarial instructions inside tool descriptions and silently mutate tool definitions after install. Here is how the attack works and how to defend against it.
AI coding assistants like Copilot and Cursor can be hijacked by hidden text in files, comments, and packages. Here's how prompt injection malware works and how Safeguard detects it.
Prompt engineering is how you steer an LLM, and it is also where a lot of application security now lives. Here is how to write prompts that resist injection and leakage.
As AI models become critical software components, the need for AI-specific SBOMs and model cards grows urgent. How the industry is extending supply chain transparency to machine learning pipelines.
MCP servers give AI agents direct tool access, but most ship unvetted. Here's how security scanning catches tool poisoning and rug-pull attacks.
Weekly insights on software supply chain security, delivered to your inbox.
Your first fix PR is minutes away.
No sales call required, even your agent can complete the purchase over MCP.