# Unplug AI (unplug-ai.org)

Scans untrusted LLM inputs for prompt injection, destructive commands and data leaks, returning flagged spans with redactions.

- Atlas card: https://inite.ai/en/atlas/unplug-ai.org
- Site: https://unplug-ai.org
- For: developers building LLM apps or agents that handle untrusted text
- Categories: security
- Use 22/100 · alive 79/100

## Used for

- screen untrusted text for prompt injection
- block destructive SQL, shell, git and file actions
- redact API keys and PII from LLM inputs and outputs

## Price

Not read yet.

## For developers

None found.
- Read 2026-10-22

## Your data

- Certifications stated: none
- Read 2026-10-22

---

Source: INITE Atlas, https://inite.ai/en/atlas/unplug-ai.org. JSON: https://inite.ai/api/atlas/unplug-ai.org. MCP: https://inite.ai/api/mcp (atlas_lookup).