Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.mindgard.ai/llms.txt

Use this file to discover all available pages before exploring further.

​
Purpose

The mindgard recon tool-discovery command lets you enumerate available tools on a target for reconnaissance purposes. Based on the findings from this tool, you can then adjust your payload strategies for deeper assessment.

​
Usage

After you have logged into your Mindgard account in the CLI, run: 
mindgard recon tool-discovery {target options}
Options --bypass — Use enhanced prompts to attempt circumvention of guardrails. Warning: bypass will fire ~100–150 additional requests against the target. For more information on setting target options refer to the recon sub-command reference and configuration files documentation. Results At the end of the recon test you will be given a link to its results page. The results page will show a list naming the most mentioned tools by the target, as well as their parameters. You may also inspect prompt-response pairs to explore queries that resulted in a divulgence of tools and parameters. Mindgard tool discovery results showing the most occurring tools and individual event logs from the most recent test. Inspecting the details of the responses may reveal a deeper view of how the target LLM interacts with backend services such as databases, code fragments, and other unsurfaced services such as internal APIs.

​
When to use it

  • Before launching attacks on a target, to first scope tools and tool-calling capabilities on the target, as well as other information that could be misused.