---
title: "Prompt Injection"
created: 2026-05-10
updated: 2026-05-10
type: concept
tags: [security, agent, safety, stub]
sources: []
---

# Prompt Injection

Prompt injection is an attack where untrusted content attempts to override, redirect, or manipulate an LLM or agent's intended instructions.

For tool-using agents, prompt injection can lead to unsafe tool calls, data exfiltration, or persistent memory contamination.

## Related

- [[agent-safety]] — Broader safety context.
- [[clawguard]] — Runtime defense against indirect prompt injection.
- [[ssl-skill-representation]] — Skill representation can interact with tool-use security.