# LLM guardrails and agent security tools — The Agents Index

> Source: https://theagentsindex.com/category/guardrails (curated, re-verified)

Libraries and APIs that check what goes into and comes out of an agent: prompt injection, data leaks and risky actions.

1 agent in this category, A to Z. Each name links to its answer-first markdown twin.

| Name | What it is | Pricing | API |
| --- | --- | --- | --- |
| [HOL Guard](https://theagentsindex.com/hol-guard.md) | Local-first runtime security layer that allows, asks or blocks risky AI coding-agent actions before they run. | Free, then $4.99/month | Yes |