> For the complete documentation index, see [llms.txt](https://docs.ox.security/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.ox.security/vibesec/agent-ai-bom/agent-ai-bom-external-saas.md). # Agent AI BOM: External SaaS On the External SaaS tab of the [Agent AI BOM](/vibesec/agent-ai-bom.md) page, you govern the third-party SaaS systems that agents in your organization are reaching into. You can track which external SaaS systems agents access, how often, and the commands they issue. Reviewing this list lets you confirm that agents are only touching authorized systems, surface unexpected integrations, and identify the developers responsible for each one so you can follow up where the access scope is not appropriate. They appear when the agent issues commands against a third-party system during a coding session, when skills or hooks the developer has configured make calls into a SaaS, or through any other path the agent uses to reach an external system.
## Table columns | Column | Description | | -------------- | --------------------------------------------------------------------------------- | | Name | The name of the external SaaS system, such as `GitHub`, `Jira`, or `Slack`. | | Total Users | The number of distinct developers whose agents have reached this SaaS. | | Total Commands | The number of distinct commands that have been issued against this External SaaS. | | Total Calls | The total number of calls (command executions) recorded against this SaaS. | | First Seen | When OX first recorded a call to this SaaS. | | Last Activity | When the most recent call was recorded. | ## Filters | Filter | Description | | --------- | -------------------------------------------------------------------------------------------------------------------------------------- | | SaaS Name | Limits the list to selected SaaS systems by name. | | Command | Shows only SaaS entries where agents have run the selected command. Useful for finding all use of a specific operation across systems. | | User | Shows only SaaS systems used by selected developers. | | Source | Filters by the source through which the SaaS was reached, such as Cursor and Claude Code. | ## Reviewing external SaaS activity Selecting an external SaaS system opens a detailed view that helps you understand how agents interact with the integration, which commands they execute, and which developers use it. The **Explore** tab provides an overview of how the external SaaS system is used across your organization. Use this view to understand adoption, identify the most frequently executed commands, and determine which developers rely on the integration most heavily.
| Section | Description | | ------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | Summary metrics |

Provides a quick overview of external SaaS activity within the current scope, as follows:

| | Most Used Commands |

Shows the commands executed against the external SaaS system and ranks them by usage.

Use this section to:

To view the complete list of commands, select View All.

| | Most Active Users |

Shows the developers who generated the most activity for the external SaaS system.

Use this section to:

To view all users who accessed the integration, select View All.

| The **Commands** tab lists the commands executed against the external SaaS system. To review the actions agents perform through the integration, identify commands with sensitive functionality, or investigate unusual command usage, open this tab. The **Users** tab lists the developers who accessed the external SaaS system through their AI agents. To identify who uses the integration, review usage levels by developer, or investigate unexpected access, open this tab. Review the list and confirm that each entry corresponds to a system you expect agents to access. A SaaS entry you did not expect, for example, an unauthorized integration, is a signal to follow up with the developers listed under Total Users. Select an entry to view the Users tab and identify who is using the integration, or open the Commands tab to review the actions performed through it. Sort by Total Calls to surface the integrations with the most activity.
--- # 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, and the optional `goal` query parameter: ``` GET https://docs.ox.security/vibesec/agent-ai-bom/agent-ai-bom-external-saas.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. 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.