Unplug AI
Actively maintained
121 installs/mo
Emerging
- For
- developers building LLM apps or agents that handle untrusted text
- Activity
- Actively maintainedrelease 11 days ago · site updated 4 months ago
- Runs as
- SDK
- 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
- Publishes llms.txt, a file written for AI assistantsunplug-ai.org ↗
- Launched on Product Hunt on Aug 29, 2026Product Hunt ↗
Figure and bar: visits/mo, estimate · year: online since
- #1
PromptGuard
Inspects requests to LLM applications and blocks prompt injection, jailbreak attempts, and personally identifiable information leaks.
12ActiveFrom $99/mo - #2
Kalpit Labs
Detects and blocks prompt injection, jailbreaks, and data leaks in LLM applications in real time.
EmergingMaintained - #3
Lakera
Detects and prevents prompt injection attacks, data leakage, and jailbreaks in AI applications with real-time threat detection.
2.9kMaintainedFree plan1993 - #4
Wardstone
Detects prompt injection attacks, jailbreaks, harmful content, and PII leakage in LLM inputs and outputs.
298ActiveFrom $199/mo - #5
SovereignShield
Blocks prompt injection attacks and prevents unauthorized actions in AI agent requests before they reach the model.
24 linking domainsActiveFrom $5 once - #6
PromptGuard ScanMCP · sign-in
Scans LLM app prompts and retrieved content for injection, jailbreak and secret leakage, failing CI builds on high-risk findings.
Little sign of useFrom $25/mo
Not it? Say what you need
betaThree tools from the Atlas for the job you describe, each with what fits and what does not.
No notes yet. What do you use Unplug AI for?
Sign in to leave a noteWhat is Unplug AI?
Scans untrusted LLM inputs for prompt injection, destructive commands and data leaks, returning flagged spans with redactions. It is listed in the Atlas under Security.
Who is Unplug AI for?
developers building LLM apps or agents that handle untrusted text
Do people use Unplug AI?
Emerging: 121 installs/mo (pypi).
Is Unplug AI still maintained?
Actively maintained: release 11 days ago · site updated 4 months ago.
What are alternatives to Unplug AI?
In Security, by use: PromptGuard, Kalpit Labs, Lakera, Wardstone, SovereignShield, PromptGuard Scan.
How we read a tool
No votes, no reviews, no vendor claims. Every week a crawler reads each tool's own site and a few public registries, and the words on the card are bands over what it read.
- Use: visits to the site (estimated), installs from npm and PyPI, presence in Chrome's usage report.
- Activity: the newest release on GitHub, npm or PyPI; the newest dated page on the site; open roles on a public jobs board.
- Price: the vendor's own pricing page, read with the date. A figure is printed only when it is on that page.
- The line and the use cases are written by us from the homepage, one tool at a time, and refused when they repeat the vendor's marketing.
How AI assistants read each site — the reading vendors ask us about — is on each tool's own visibility page.
How we read every tool → · By INITE Atlas Desk
Cookies
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.