LLM01:2025
Prompt Injection
Prompt injection happens when an attacker uses instructions in user input, documents, webpages, tickets, or tool output to change the model's intended behavior.
Open guideOWASP Top 10 for LLM Applications 2025
A practical guide to prompt injection, sensitive data exposure, RAG boundaries, model supply chain, unsafe output handling, excessive agency, and the rest of the OWASP LLM Top 10.
Prompt Injection
Open the category guide
Sensitive Information Disclosure
Open the category guide
Supply Chain
Open the category guide
Data and Model Poisoning
Open the category guide
Improper Output Handling
Open the category guide
Excessive Agency
Open the category guide
System Prompt Leakage
Open the category guide
Vector and Embedding Weaknesses
Open the category guide
Misinformation
Open the category guide
Unbounded Consumption
Open the category guide
Untrusted input
Model context
Action validation
Tools and data
Action record
The list is most useful when each category maps to a concrete system boundary: who can influence the model, what data can enter context, which tools can act, and what control stops a bad path before it reaches production.
Category guides
Each guide explains the risk, walks through an example and lists controls and questions for the engineering team.
LLM01:2025
Prompt injection happens when an attacker uses instructions in user input, documents, webpages, tickets, or tool output to change the model's intended behavior.
Open guideLLM02:2025
How AI systems can expose secrets, regulated data, customer records, proprietary material, or internal context through outputs, logs, tools, or retrieval.
Open guideLLM03:2025
Risks from compromised or unreviewed models, datasets, plugins, packages, MCP servers, prompts, infrastructure, and vendors in an AI application.
Open guideLLM04:2025
Data and model poisoning introduces manipulated data or model artifacts that change the system's behavior. Training, fine-tuning and embedding pipelines all need integrity checks.
Open guideLLM05:2025
Improper output handling occurs when an application passes generated content to a browser, shell, database, tool or other component without the checks required by that destination.
Open guideLLM06:2025
Excessive agency occurs when an AI system has more autonomy, permissions, tools, or action scope than the task requires.
Open guideLLM07:2025
System prompt leakage happens when hidden instructions, policy text, tool rules, internal routing logic, or operational context is exposed through model responses.
Open guideLLM08:2025
Vector and embedding weaknesses affect RAG systems when embeddings, vector stores, chunking, metadata, retrieval filters, or similarity logic expose or distort context.
Open guideLLM09:2025
Misinformation occurs when an AI system produces false, unsupported, outdated, or misleading output that users or downstream systems treat as reliable.
Open guideLLM10:2025
How attackers or faulty workflows can drive excessive model calls, token use, context growth, tool loops, compute cost, or service disruption.
Open guideUse it in review
For each relevant category, write down the affected components, the expected behavior and the test that checks it. Assign an owner and rerun the test when the model or application changes.
Read the official OWASP 2025 PDFMap each category to runtime components.
Test direct and indirect prompt paths.
Inventory MCP, OAuth, and tool authority.
Review RAG source, tenant, and vector boundaries.
Set launch criteria with named owners.
Keep regression probes after remediation.