# Guardrail Actors

## What are **Guardrail Actors?**

Guardrail actors are individuals, groups, or entities responsible for carrying out malicious activities targeting your AI agents, MCP endpoints, and autonomous systems. They are often motivated by financial gain, espionage, ideology, or disruption. Guardrail actors targeting agentic systems may attempt prompt injections, tool abuse, data exfiltration through agent interactions, or unauthorized access to agent capabilities. They can range from lone hackers to organized crime groups, nation-states, or insider threats.

## **Key Metrics to Monitor**

**Critical Actors**: Guardrail actors posing a high risk to your agentic systems due to their capability and intent

**Active Actors**: The total number of guardrail actors currently engaging in malicious activities against agent components

**Guardrail Activity Timeline**: Tracks the frequency and volume of attacks over time (e.g., agent component invocations, tool abuse attempts)

**Guardrail Actor Map**: Geographically maps the origin of guardrail actors targeting your autonomous systems

<figure><img src="/files/1odNB8t8eI40C1wG14H0" alt="" width="563"><figcaption></figcaption></figure>


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://ai-security-docs.akto.io/agentic-guardrails/concepts/threat-actors.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.