Agent Guidelines

Agent guidelines are secure coding instructions that OX provides to AI coding agents to help them generate code without introducing vulnerabilities.

When a developer submits a prompt to an AI coding agent, OX analyzes the prompt and determines which vulnerabilities could potentially be introduced by implementing the requested functionality. OX then returns the relevant secure coding guidance based on the predicted vulnerability and the programming language being used.

The guidance is provided to the AI coding agent before code generation begins and is applied automatically in the background. As a result, the agent generates code using secure implementation patterns from the outset, reducing the likelihood of introducing security vulnerabilities.

The Agent Guidelines page shows all guidelines available to your organization's AI coding agents. Each guideline targets a specific vulnerability and programming language combination.

Guidelines list

Use the filters and search box above the list to find specific guidelines.

Column	Description
Toggle	Enables or disables the guideline. When enabled, OX can provide the guideline to AI coding agents when the prompt matches the guideline's activation criteria. When disabled, the guideline is not returned.
Name	The guideline name and target language. For example, sql-injection-prevention (Python).
Category	The OX category the guideline belongs to. Agent guidelines currently belong to the Code Security category.
Language	The programming language(s) the guideline targets.
Author	The author of the guideline. OX-provided guidelines are labeled Created by OX.

Filtering guidelines

Field	Description
Language	Filters the list by programming language. Select All to display guidelines for all supported languages.
Status	Filters the list by guideline status (Enabled or Disabled). Select All to display both.
Search	Searches for guidelines by name.

Select a guideline to view its details.

Viewing guideline details

Each guideline includes the following information:

Section	Description
Description	A summary of the vulnerability the guideline is designed to prevent.
Activation Criteria	The conditions OX evaluates in a developer's prompt to determine whether the guideline should be provided to the AI coding agent.
Instructions	Secure coding guidance that helps the AI coding agent generate code without introducing the targeted vulnerability.
Code Samples	Example implementations that demonstrate the recommended secure coding pattern.

OX provides the guidance and examples to the AI coding agent in the background. Developers do not interact with the guideline directly. Instead, the agent uses the guidance during code generation to produce code that follows the recommended secure implementation patterns.