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

# Prompt Injection & Safe Metadata

> Understand what UseAgents checks during deployment and how to keep tool metadata safe for AI agents.

Before each deployment, UseAgents scans tool metadata for content that could override AI behavior or hijack downstream agents. This page explains what is checked and how to keep your metadata safe.

## What we check

Tool metadata is scanned before each deployment. The following fields are checked:

* **Name** and **slug**
* **Description** and **tagline** (short description)
* **Categories** and **tags**
* **Input shape** and **output shape**
* **Common pitfalls**
* **Quickstart** usage code and install commands (per language)

Install commands must start with an allowed package manager (`npm`, `pnpm`, `yarn`, `bun`, `pip`, `uv`, `cargo`, `go`, `gem`, `composer`, or `docker`). Commands outside that list can fail verification because agents may treat them as authoritative install steps.

If any field is flagged, the deployment fails and the UI shows which field failed, why, and how to fix it.

## What prompt injection means here

Prompt injection is when natural-language fields contain instructions intended to:

* Override AI behavior or system prompts
* Jailbreak or bypass safety restrictions
* Exfiltrate data or hijack downstream tool consumption

Examples of problematic content include:

* `Ignore previous instructions`
* `You are now`
* `System prompt:`
* Hidden instructions inside code blocks
* Jailbreak or bypass-related language

## Avoid these patterns

| Pattern                       | Example                                                  |
| ----------------------------- | -------------------------------------------------------- |
| Override instructions         | `Ignore previous instructions`, `Disregard prior`        |
| Role changes                  | `You are now`, `New instructions:`                       |
| System prompt injection       | `System prompt:`, `System:`                              |
| Code blocks with instructions | Instructions hidden in code blocks or special formatting |
| Bypass language               | `Jailbreak`, `Bypass safety`                             |

## Write safe metadata instead

Keep descriptions factual and neutral. Focus on:

* What the tool does
* Integrations and use cases
* How agents should use it

Describe the tool. Do not try to instruct the AI that reads it.

## If deployment fails

1. Open the deployment details page.
2. Open the **Verification** step.
3. Review the flagged fields, reasons, and suggested fixes.
4. Use **Edit Tool** to update the metadata.
5. Redeploy.

## Safe writing checklist

* Describe product behavior, capabilities, and integration points.
* Avoid telling the reading AI what to do or ignore.
* Keep content plain, specific, and free of hidden instructions.
* Remove roleplay, jailbreak language, and system-prompt framing.