doc/user/application_security/analyze/duo.md
{{< details >}}
{{< /details >}}
{{< collapsible title="Model information" >}}
{{< /collapsible >}}
{{< history >}}
{{< /history >}}
GitLab Duo Vulnerability Explanation can help you with a vulnerability by using a large language model to:
GitLab Duo can also automatically analyze critical and high severity SAST vulnerabilities to identify potential false positives. For more information, see SAST false positive detection.
<i class="fa-youtube-play" aria-hidden="true"></i> Watch an overview
Prerequisites:
To explain the vulnerability:
In the top bar, select Search or go to and find your project.
Select Secure > Vulnerability report.
Optional. To remove the default filters, select Clear ({{< icon name="clear" >}}).
Above the list of vulnerabilities, select the filter bar.
In the dropdown list that appears, select Tool, then select all the values in the SAST category.
Select outside the filter field. The vulnerability severity totals and list of matching vulnerabilities are updated.
Select the SAST vulnerability you want explained.
Do one of the following:
/vulnerability_explain.The response is shown on the right side of the page.
On GitLab.com this feature is available. By default, it is powered by the Anthropic claude-3-haiku
model. GitLab cannot guarantee that the large language model produces results that are correct. Use the
explanation with caution.
The following data is shared with third-party AI APIs: