# guidesยท4 published
Guides
Written for one task each, and built on the same sourced register.
OWASP Top 10 for LLM Applications 2026: the list and what changed
The 2026 OWASP Top 10 for LLM Applications, entry by entry, with what moved since 2025 and which IDs now mean something different.
updated
MCP security risks: what has gone wrong, and what the spec says
Documented Model Context Protocol attacks, the risks the MCP specification itself names, and a checklist to run before you connect a server.
updated
Prompt injection examples: documented cases, labeled incident or demo
Dated prompt injection cases from Microsoft 365 Copilot, Slack AI, Gemini, ChatGPT, coding assistants and more, each labeled as a real incident or a research demonstration, with the source.
updated
AI acceptable use policy: a starter template tied to the risks
A short AI acceptable use policy you can copy and adapt, with each clause linked to the security risk and documented cases it answers. No email required.
updated