> For clean Markdown of this page, append .md to its URL. For the complete documentation index, see https://www.superagent.sh/llms.txt.


A security worker is a built-in unit of security execution that runs a defined job against protected software.

# Security workers

Choose a security worker after connecting the software you want to protect.
Each worker page explains its requirements, setup, results, and controls.

## Choose by outcome

| You want to | Security worker |
| --- | --- |
| Review code and dependency changes before merge | [PR Security](https://www.superagent.sh/docs/security-workers/pr-security) |
| Generate policy-checked dependency update pull requests | [Secure Dependency Updates](https://www.superagent.sh/docs/security-workers/secure-dependency-updates) |
| Find exploitable paths across software you already ship | [Red Team](https://www.superagent.sh/docs/security-workers/red-team) |
| Check external content before an agent consumes it | [Context Guardrails](https://www.superagent.sh/docs/security-workers/agent-guardrails/context) |
| Monitor or block risky actions where an agent runs | [Runtime Guardrails](https://www.superagent.sh/docs/security-workers/agent-guardrails/runtime) |

Security workers can work together. For example, a repository can use PR
Security on every change and run deeper Red Team campaigns on a schedule.

---
Source: https://www.superagent.sh/docs/security-workers
Index: https://www.superagent.sh/llms.txt