> ## Documentation Index
> Fetch the complete documentation index at: https://docs.vijil.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# The Trust Score

> A quantitative framework for measuring agent trustworthiness across reliability, security, and safety.

<Tip>
  **TL;DR:** The Trust Score quantifies how trustworthy an [AI agent](/owner-guide/register-agents/what-is-an-agent) is in production on a scale from 0 to 100. A score at or above 70 meets the deployment threshold. The Trust Score breaks down into three dimensions: [Reliability](/concepts/trust-score/reliability), [Security](/concepts/trust-score/security), and [Safety](/concepts/trust-score/safety).
</Tip>

Trust is the willingness to accept risk in exchange for expected benefit. When you trust a person, a machine, or an organization, you are making a calculation often unconsciously about whether the reward of cooperation outweighs the risk of betrayal.

Vijil evaluates LLM trustworthiness across 3 critical dimensions. For each dimension, it assesses vulnerability to several attack vectors. Each attack vector is treated as one evaluation module. Each module contains one or more tests.

## What the Trust Score Measures

| Score | Status     | What It Means                                    |
| ----- | ---------- | ------------------------------------------------ |
| ≥ 70  | **Passed** | Agent meets the deployment threshold             |
| \< 70 | **Failed** | Agent requires remediation before production use |

Each score breaks down into three dimensions:

| Dimension                                            | Core Question                                     | Example Failures                                      |
| ---------------------------------------------------- | ------------------------------------------------- | ----------------------------------------------------- |
| **[Reliability](/concepts/trust-score/reliability)** | Does the agent do what it is supposed to do?      | Hallucinations, inconsistent responses, task failures |
| **[Security](/concepts/trust-score/security)**       | Can the agent resist adversarial manipulation?    | Prompt injection, data leakage, jailbreaks            |
| **[Safety](/concepts/trust-score/safety)**           | Does the agent stay within acceptable boundaries? | Policy violations, harmful content, bias              |

<Warning>
  A passing Trust Score reflects performance against tested [Scenarios](/concepts/evaluation-components/scenario). The Trust Score does not guarantee absence of all vulnerabilities, as coverage depends on the [Harness](/concepts/evaluation-components/harness) configuration and [Probe](/concepts/evaluation-components/probe) selection.
</Warning>

<Columns cols={1}>
  <Card title="Reliability" icon="badge-check" href="/concepts/trust-score/reliability" arrow="true">
    Learn more about Reliability
  </Card>

  <Card title="Safety" icon="lock-keyhole" href="/concepts/trust-score/safety" arrow="true">
    Learn more about Safety
  </Card>

  <Card title="Security" icon="shield-check" href="/concepts/trust-score/security" arrow="true">
    Learn more about Security
  </Card>
</Columns>

## Next Steps

<CardGroup cols={2}>
  <Card title="Reliability" icon="circle-check" href="/concepts/trust-score/reliability">
    Deep dive into correctness, consistency, and robustness
  </Card>

  <Card title="Security" icon="lock" href="/concepts/trust-score/security">
    Deep dive into confidentiality, integrity, and availability
  </Card>

  <Card title="Safety" icon="shield" href="/concepts/trust-score/safety">
    Deep dive into containment, compliance, and transparency
  </Card>

  <Card title="Run an Evaluation" icon="play" href="/owner-guide/getting-started/introduction">
    Get a Trust Score for your agent
  </Card>
</CardGroup>