# AIVSS10 - Agent Goal and Instruction Manipulation

> Prompt injection and goal-hijacking that subverts the agent's core objective.

- **Category**: Owasp Aivss
- **Subcategory**: core_security_risks
- **Canonical URL**: https://designpattern.fyi/owasp_aivss/aivss10_goal_instruction_manipulation/

---

## Description
'**Intent**: Prevent adversaries from redirecting an autonomous agent away from its intended objectives through prompt injection.

**Context**: Agents operate with defined goals and autonomy. Attackers can inject instructions through various channels to override or subtly shift the agent's primary objective, leading to unauthorized actions. This is the classic prompt injection vector adapted for agentic systems.

**Solution**: Implement goal validation and integrity checks. Use immutable goal definitions. Apply input sanitization at all agent interfaces. Monitor for goal drift. Implement behavioral anomaly detection. Use goal-guarding frameworks. Separate goal definitions from execution logic.'



## Use Cases
Use when building autonomous agents that operate with defined goals and interact with external inputs.





## Trade-offs


### Advantages

- Maintains agent purpose integrity

- Prevents objective manipulation

- Enables goal compliance monitoring

- Supports safe autonomy




### Considerations & Drawbacks

- Goal drift detection can be subtle

- May limit agent flexibility

- Requires continuous behavioral monitoring







---
**Reference**: [Original Source](https://aivss.owasp.org/)