Skip to the content
Know your tech before you buy it. Makers: get listed from $49/mo

OpenSecureAI Scanner

opensecureai.com

  • Free plan
  • Open source
  • Windows
  • macOS
  • Linux
  • Web
  • API
  • Self-hosted
8.5 Club score Visit opensecureai.com

What OpenSecureAI Scanner is

OpenSecureAI Scanner checks untrusted text for patterns associated with prompt injection, jailbreaks, system-prompt leaks and data exfiltration. Its scanPrompt library API returns a score from 0 to 100, a risk level and findings for individual rules. Developers can use it through an npm package, CLI, GitHub Action or REST API; the package targets Node 18+ and has no runtime dependencies. Authenticated hosted scans add detections for obfuscation, indirect injection, tool abuse, multilingual overrides and de-obfuscation. The LLM Gateway can forward prompts to a selected OpenAI, Anthropic, xAI or Groq provider and scan the response. Documentation says authenticated scans save a summary to the dashboard without storing raw prompt text, and gateway provider keys are not stored or logged. Free access lists 2,000 API requests per month; Pro costs $49 a month and lists 50,000 requests monthly. Paid checkout is not self-serve, so customers must contact sales for setup. The maker identifies AI application teams, agent and MCP developers, security reviewers, learners and red-teamers as audiences.

Who it suits

OpenSecureAI Scanner suits developers building AI applications, agents or MCP systems, as well as security and compliance reviewers. Learners and red-teamers may also use its scanning tools.

Good to know, and what to watch

  • Available as an npm package, CLI, GitHub Action and REST API.
  • Scan results include a score, risk level and rule findings.
  • Authenticated scans do not store raw prompt text.
  • Gateway provider keys are not stored or logged.
  • Free access lists 2,000 API requests per month.
  • Pro costs $49 a month.
  • Paid setup requires contacting sales.
  • The npm package targets Node 18+.

Team

—

Free

Free

Pro

$49/mo

Free plan

Getting started

  1. Open the OpenSecureAI website
  2. Use the browser tools or npm packages for free access
  3. Install the npm package on Node 18 or later
  4. Integrate through the CLI, GitHub Action, or REST API
  5. Authenticate to access hosted advanced detections
  6. Contact sales to arrange a paid plan

Limits to check

The Free plan provides 2,000 API requests per month and 30 requests per minute per key. Pro provides 50,000 requests monthly and 120 requests per minute per key; Team lists 250,000 requests monthly and 300 requests per minute per key, with custom billing.

The Club's review

Overview

OpenSecureAI Scanner checks untrusted text for prompt injection and related AI security risks, with options for local tools and an authenticated hosted API. It suits developers and security teams adding text checks to an application or review workflow. Its appeal is the mix of free entry points and richer hosted detections, while API quotas and sales-led paid setup constrain growth.

The scanner focuses on prompt-injection, jailbreak, system-prompt-leak and data-exfiltration patterns. That makes it a useful screening layer for those risks, rather than a complete assessment of AI system security.

Key features

The scanPrompt library returns a score from 0 to 100, a risk level and findings for individual rules, giving developers more to work with than a single pass-or-fail result. It is offered as an npm package, CLI, GitHub Action and REST API. The package targets Node 18 and later and has no runtime dependencies, a practical fit for Node projects and build workflows.

In-browser tools and npm packages are free and open. Anonymous API requests use the basic engine and are rate-limited by IP. Authenticated hosted calls add detections for obfuscation and encoding evasions, indirect injection, tool abuse, multilingual overrides and de-obfuscation. Those capabilities make the hosted engine the stronger option for teams concerned about less direct attacks; using it requires an API key.

The LLM Gateway can route prompts to a selected OpenAI, Anthropic, xAI or Groq provider and model, then scan the response. Authenticated scans save a summary to the dashboard without storing raw prompt text, and provider keys are not stored or logged. These handling terms may suit teams that want gateway support while limiting retained prompt data.

OpenSecureAI also describes its wider platform as covering threat intelligence and learning resources, alongside protection against threats such as data poisoning and model theft. The scanner’s stated detection scope is narrower. The company says it responds to vulnerability reports within 48 hours.

Pricing

The Free plan is billed at $0/month and allows 2,000 API requests per month, with a limit of 30 requests per minute per key. It includes in-browser tools and npm packages, and the hosted advanced engine with an API key. It is a sensible starting point for learning or low-volume checks, but the request cap and rate limit may quickly constrain a production workflow.

Pro costs $49 a month, billed $49/month. It raises the allowance to 50,000 API requests per month and 120 requests per minute per key, and adds hosted AI remediation, LLM Gateway completions and priority email support. This is the defined paid tier for teams that need more capacity and gateway features. Paid checkout is not self-serve; customers must contact sales to be set up.

Team has custom pricing and includes 250,000 API requests per month and 300 requests per minute per key. Team seats and SSO, along with custom rules and an SLA, are planned. The larger quotas may suit higher-volume use, but those planned features should not be treated as current inclusions.

Platforms

OpenSecureAI Scanner supports API, Linux, macOS, web and Windows. Its npm package, CLI and GitHub Action also give developer teams several ways to connect scanning with existing code and build workflows.

Who it's for

This is a good fit for AI application teams, agent and MCP developers, security and compliance reviewers, learners and red-teamers who need focused checks for risky text. Developers who want local tools can start with the free package or browser tools; teams that need the hosted engine, gateway completions or larger quotas should weigh the API limits and sales setup.

Pros and cons

  • Pros: Multiple ways to integrate, including an npm package, CLI, GitHub Action and REST API, make it adaptable to developer workflows.
  • Pros: The scan result combines a score, risk level and per-rule findings, which can help teams interpret why text was flagged.
  • Pros: Authenticated hosted scans add detection coverage for indirect and evasive attacks, while raw prompt text is not stored.
  • Cons: Free API use is capped at 2,000 requests per month and 30 requests per minute per key, limiting sustained use.
  • Cons: Paid access requires contacting sales, adding a setup step for teams that want to move beyond the free tier.
  • Cons: The scanner’s detection scope is focused on untrusted text patterns, so it should not be mistaken for broad AI system security coverage.

Alternatives

Choose AIRTA Red Team if you want a free, open-source option with no license fee or subscription and can bring your own LLM API key. PyRIT is another free, open-source choice when a Python environment and configured AI endpoints suit your setup. Augustus is free and Apache 2.0 licensed, with provider credentials potentially needed for API use. Basilisk is a free AGPL-3.0 option distributed as a CLI, desktop app, Docker image or source, for authorized use.

Promptfoo offers a free Community plan with 10k red-team probes per month, LLM evaluation features and local or self-hosted operation, making it an option for readers prioritizing those evaluation and deployment terms. PromptGuard offers 20,000 scans a month on its free plan and a $19 a month Team plan, which may fit readers comparing scan volume and a lower stated paid price. F5 BIG-IP APM is a paid option with a free trial and perpetual licensing across BIG-IP Virtual Editions, hardware or hybrid environments. Project Moonshot is another free alternative.

Browse more options in AI Security Testing Tools and AI Red Teaming Tools.

Verdict

OpenSecureAI Scanner is best for developers and AI security teams that want a focused text-scanning layer with flexible integration paths and hosted detections for evasive threats. The free tools make it approachable, and Pro adds defined capacity and gateway features. Look elsewhere if you need broader AI security coverage, higher free API limits or a paid plan you can activate without contacting sales.

The verdict

OpenSecureAI Scanner offers several ways to scan text for common AI security risks, with added hosted detections for authenticated calls. Factor in the API limits and sales-led setup for paid access.

Questions people ask

Is OpenSecureAI Scanner free?

Yes. The Free plan is billed at $0/month and includes in-browser tools, npm packages, and 2,000 API requests per month. Pro is $49 a month.

Which platforms does it support?

It supports API, Linux, macOS, web, and Windows.

What does the scanner detect?

It detects prompt-injection, jailbreak, system-prompt-leak, and data-exfiltration patterns. Hosted authenticated scans add obfuscation, indirect injection, tool abuse, multilingual override, and de-obfuscation detections.

Can it scan model responses?

Yes. The LLM Gateway can forward prompts to a selected OpenAI, Anthropic, xAI, or Groq provider and scan the response.

Does it store prompts or provider keys?

Authenticated scans save a summary to the dashboard but do not store raw prompt text. Gateway provider keys are not stored or logged.

How do I buy a paid plan?

Paid checkout is not self-serve. Customers should contact sales for setup.

What the maker publishes

Agent Guard
Agent Guard audits OpenAI, Anthropic and MCP tool definitions for excessive agency, code-execution and SSRF sinks, secret access and cross-tool exfiltration. source
API
The public REST API exposes scan, unified analysis, agent-guard, gateway, events and threat-feed endpoints. source
CLI and CI
The scanner and firewall packages include command-line interfaces, and the scanner provides a GitHub Action for pull-request gating. source
Company founding
OpenSecureAI states that it was founded in 2026 and launched its prompt-injection scanner and platform during 2026. source
Company history
The About page says OpenSecureAI was founded in 2026 and is global and remote-first. source
Developer use
The scanner is available as an npm package, CLI, GitHub Action, and REST API, and its package targets Node 18+ with zero runtime dependencies. source
Documentation depth
Documentation includes installation, library API, CLI flags and exit codes, GitHub Action configuration, REST examples, observability fields, system-prompt auditing and threat-feed queries. source
Founded
2026 source
Free access
The maker says its in-browser tools and npm packages are free and open, and the anonymous API uses the basic engine with IP rate limiting. source
Gateway integrations
The gateway names OpenAI, Anthropic, xAI and Groq as supported providers and accepts customer-supplied keys. source
Headquarters
The company describes itself as global and remote-first rather than listing a physical headquarters. source
Hosted engine
Authenticated hosted API calls add private detections for obfuscation and encoding evasions, indirect injection, tool abuse, multilingual overrides, and de-obfuscation. source
Independent domain assessment
ScamAdviser describes opensecureai.com as very likely safe, citing valid SSL and DNSFilter safety signals. source
Independent package publisher
The npm profile aistar lists three OpenSecureAI packages: scanner 0.2.0, firewall 0.2.0 and agent-guard 0.1.0. source
Independent reputation score
Gridinsoft reports a 72/100 trust score for opensecureai.com and says no major malware or phishing detections were found. source
Integrations
The LLM Gateway can forward prompts to a selected OpenAI, Anthropic, xAI, or Groq provider/model and scan the response. source
Intended users
The maker identifies AI application teams, agent and MCP developers, security and compliance reviewers, learners, and red-teamers as audiences for its platform. source
Key handling
The docs state that LLM Gateway provider keys are never stored or logged. source
License status
OpenSecureAI says its core engine and npm packages are open source, while the hosted advanced engine contains private detections; the pages do not name a specific open-source license. source
Limit: account and enterprise controls
Team seats, SSO, custom rules and SLA support are marked planned, and paid checkout currently requires contacting sales. source
Limit: domain transparency
ScamAdviser flags free registration email addresses and low Tranco traffic rank as negative signals. source
Limit: independent verification
Gridinsoft characterizes the domain as reliable but still requiring verification rather than fully validated. source
LLM Gateway
The gateway scans an input, forwards it to a selected model provider, scans the response and can mask leaked secrets or PII or block risky traffic. source
Observability
LLM Observability aggregates injection attempts, blocks and anomalies from API events while instructing users to send labels and metadata instead of raw prompts or responses. source

Checked against the maker's pages on 15 Oct 2026.