AI Security & Responsible AI Cheat Sheet

This content was generated with the assistance of AI and should be verified against the official documentation of each tool and framework before being relied on in production.

This section’s bibliography lists the reference material consulted while preparing these pages.

A single-page index of quick back-links to every page in this sub-section, grouped the same way as the navigation. It was written on 2026-10-01 against the OWASP Top 10 for LLM Applications 2026, the OWASP Top 10 for Agentic Applications 2026, MITRE ATLAS, NIST AI RMF 1.0 with AI 600-1, the EU AI Act as amended by the Digital Omnibus on AI, garak 0.17.0, PyRIT 1.1.0, promptfoo 0.123.1, NeMo Guardrails 0.24.1, Guardrails AI 0.11.0, Presidio 2.2.364, LangChain 1.4.3 and Spring AI 2.0.1; the full list is the version baseline on the landing page.

The downloadable PDF is a separate, single A4 page meant for printing. It states the version baseline and covers:

  • the trust boundaries of an LLM application and the threat-model flow;

  • the OWASP Top 10 for LLM Applications 2026 with its 2025 and 2023 mapping;

  • the OWASP Top 10 for Agentic Applications (ASI01 to ASI10);

  • the prompt-injection defence layers;

  • tool and MCP least-privilege rules;

  • output-handling rules;

  • sensitive information, hidden context and the RAG and vector checklist;

  • supply-chain controls;

  • consumption limits and the denial-of-wallet bound;

  • misinformation and hallucination controls;

  • the guardrail options table;

  • red-teaming commands for garak, promptfoo and PyRIT;

  • LLMSecOps and securing AI-assisted development;

  • the NIST AI RMF function map and the AI 600-1 risks;

  • the dated EU AI Act timeline, including the Digital Omnibus on AI (Regulation (EU) 2026/1744);

  • the RAISE and responsible-AI checklist.

Overview — AI Security & Responsible AI.

Foundations and OWASP lists — Trust Boundaries and Threat Modeling, OWASP Top 10 for LLM Applications and OWASP Top 10 for Agentic Applications.

Risks and defences — Prompt Injection, Sensitive Information and Hidden Context, Excessive Agency and Tool Security, Improper Output Handling, RAG and Vector Security, Supply Chain Security, Unbounded Consumption and Denial of Wallet and Misinformation and Hallucination Risk.

Controls and processes — Guardrails, AI Red Teaming, LLMSecOps and Securing AI-Assisted Development.

Governance and regulation — NIST AI RMF, EU AI Act and Responsible AI Practices.

The one formula the consumption section of the sheet builds on — the worst-case spend for one key in a window, explained on Unbounded Consumption and Denial of Wallet:

Source: OWASP GenAI Security Project: Top 10 for LLM Applications and NIST: AI Risk Management Framework for the lists the sheet summarises.

Download the AI Security & Responsible AI Cheat Sheet (PDF)

References

The PDF summarises the pages above; each source is cited in full on the page that covers it, and in the bibliography.