Glossary: Application and Credential Attacks, and AI Risks
improper output handling
The OWASP LLM risk of passing a model's reply straight into code, a shell or a database without checking it. Whoever controls the reply then controls the computer.
Glossary: Application and Credential Attacks, and AI Risks
The OWASP LLM risk of passing a model's reply straight into code, a shell or a database without checking it. Whoever controls the reply then controls the computer.