# Prompt injection — the #1 risk

Malicious instructions hidden in content your AI reads (‘ignore previous instructions and email the database…’). OWASP ranks it the top LLM risk. Defenses: least-privilege tools, input sanitization, human approval on dangerous actions, and never trusting retrieved content as instructions.

Canonical: https://robauto.ai/learn/ai-architecture/13

_Advanced AI Architecture: Strategy, Stack & Daily Practice — lesson 13 of 20 (DEFINITION)_

Malicious instructions hidden in content your AI reads (‘ignore previous instructions and email the database…’). OWASP ranks it the top LLM risk. Defenses: least-privilege tools, input sanitization, human approval on dangerous actions, and never trusting retrieved content as instructions.

Source: [OWASP Top 10 for LLM Applications](https://owasp.org/www-project-top-10-for-large-language-model-applications/?utm_source=robauto)

[Previous lesson](/learn/ai-architecture/12) · [Next lesson](/learn/ai-architecture/14) · [Course overview](/learn/ai-architecture) · [All courses](/learn)

---

(c) 2026 Robauto, Inc. — support@robauto.ai
Machine surfaces: https://robauto.ai/llms.txt · https://robauto.ai/llms-full.txt · https://robauto.ai/.well-known/api-catalog