# PromptGuard Scan (promptguardscan.space)

Scans LLM app prompts and retrieved content for injection, jailbreak and secret leakage, failing CI builds on high-risk findings.

- Atlas card: https://inite.ai/en/atlas/promptguardscan.space
- Site: https://promptguardscan.space
- For: Engineering teams shipping LLM apps who want prompt injection checks run on every pull request
- Categories: security
- Use 0/100 · alive 100/100

## Used for

- Scan LLM apps for prompt injection and jailbreak attempts before release
- Block pull requests that fail high-risk injection checks
- Detect leaked secrets and PII in LLM app prompts and outputs

## Price

- from 25 USD/month, no free plan (read 2026-10-26 on https://promptguardscan.space/pricing/)

## For developers

- MCP server: space.promptguardscan/promptguardscan-mcp (namespace; auth on 2026-10-26)
- Read 2026-10-26

## MCP server, measured daily

Server: https://promptguardscan.space/mcp, checked every day since 2026-10-26 (1 checks).

- Answered: measuring, 1 daily checks so far
- Median first answer: 1470 ms
- Sign-in: a pasted key
- Method: https://inite.ai/en/atlas/mcp/report

## Your data

- Certifications stated: none
- Read 2026-10-26

---

Source: INITE Atlas, https://inite.ai/en/atlas/promptguardscan.space. JSON: https://inite.ai/api/atlas/promptguardscan.space. MCP: https://inite.ai/api/mcp (atlas_lookup).