Back to Resources
Security Standard

OWASP Top 10 for LLMs (2025)

The landscape of AI security is moving fast. The 2025 update to the OWASP Top 10 introduces critical new risks like System Prompt Leakage and Vector Weaknesses.

The Top 10 Vulnerabilities

Here is the definitive list of risks you need to secure against in 2025.

LLM01

Prompt Injection

Attackers manipulate LLM input to override system instructions. Includes direct jailbreaks and indirect injection via external data sources.

LLM02

Sensitive Information Disclosure

LLMs inadvertently revealing PII, proprietary algorithms, or confidential business data in their responses.

LLM03

Supply Chain Vulnerabilities

Risks from third-party models, datasets, and plugins. Compromised pre-trained models can contain backdoors.

LLM04

Data & Model Poisoning

Manipulation of training data or fine-tuning datasets to introduce biases or vulnerabilities into the model.

LLM06

Excessive Agency

New for Agents: Granting LLMs too much autonomy to execute actions (e.g., reading emails, deleting files) without human approval.

LLM07

System Prompt Leakage

New Entry: Attackers tricking the model into revealing its internal system prompt, exposing business logic and intellectual property.

Securing Against the Top 10

Traditional security tools are insufficient for these semantic threats. You need a purpose-built AI security platform.

Railguard's Defense Matrix

  • For LLM01 (Injection): Our heuristic and intent-based firewall blocks malicious prompts before they reach the model.
  • For LLM02 (Data Leakage): Real-time PII redaction ensures sensitive data is never sent to external model providers.
  • For LLM06 (Agency): Our "Human-in-the-loop" policy engine requires approval for high-risk actions.

Audit Your AI Stack

Run a free automated scan to see if your applications are vulnerable to the OWASP Top 10.

OWASP Top 10 for LLM Applications (2025) | Railguard AI | Railguard AI