OpenSecureAI Scanner

Overview

OpenSecureAI Scanner checks untrusted text for prompt-injection and related risks, with options ranging from in-browser tools and a local npm package to an authenticated hosted API. It best suits developers and AI security teams who want to add text screening to a workflow; its free entry points are broad, but API quotas and the contact-sales setup for paid plans shape its appeal.

The scanPrompt library returns a 0–100 score, a risk level and findings for individual rules. The scanner targets prompt injection, jailbreaks, system-prompt leaks and data-exfiltration patterns. That makes it useful as one screening layer, rather than a complete security program: the published scope centers on untrusted text and does not establish coverage for every threat to an AI system.

Key features

Developers can use the scanner through an npm package, CLI, GitHub Action or REST API. The package targets Node 18 and later and has no runtime dependencies, a practical fit for teams integrating checks into Node-based applications or build workflows. In-browser tools and npm packages are free and open; anonymous API use is rate-limited by IP and runs the basic engine.

Authenticated hosted calls add detections for obfuscation and encoding evasions, indirect injection, tool abuse, multilingual overrides and de-obfuscation. This is the clearest reason to use the hosted engine when the basic checks are not enough, although accessing it through the free API tier requires an API key and remains subject to a monthly request cap.

The LLM Gateway can forward prompts to a selected OpenAI, Anthropic, xAI or Groq provider and model, then scan the response. Documentation says authenticated scans save a summary to the dashboard but do not store raw prompt text; provider keys used with the gateway are not stored or logged. The company says it responds to vulnerability reports within 48 hours.

Pricing

OpenSecureAI is freemium. The Free plan is $0/month and includes 2,000 API requests per month, 30 requests per minute per key, in-browser tools and npm packages, plus the hosted advanced engine with an API key. It suits evaluation or modest-volume use, but the request cap and rate limit may constrain sustained production traffic.

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 published paid option for teams that need materially more capacity or gateway access. Paid checkout is not self-serve: customers must contact sales to be set up.

Team has custom pricing and is billed Custom. It provides 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 rather than current inclusions, so buyers needing those capabilities should not treat them as available features.

Platforms

OpenSecureAI Scanner supports API, Linux, macOS, web and Windows. Its npm package and CLI suit developer workflows, while web tools offer a browser-based route. Both deployment modes are supported.

Who it's for

The platform is aimed at AI application teams, agent and MCP developers, security and compliance reviewers, learners and red-teamers. Developers looking to screen text through an API or build pipeline have the most directly defined use case. Teams seeking broader AI security work should weigh whether this scanner’s stated text-pattern focus matches their needs.

Pros and cons

• Pros: Free browser and package access make it possible to start without a paid plan; multiple integration formats suit different developer workflows.
• Pros: Authenticated hosted scans extend detection to evasions, indirect injection and tool abuse, while the documented handling avoids retaining raw prompt text.
• Cons: The free API allowance is 2,000 requests monthly, with a 30-per-minute limit per key.
• Cons: Paid access requires contacting sales, and Team’s seats, SSO, custom rules and SLA are planned, not included as current capabilities.

Alternatives

For a free option from the AI Verify Foundation, Project Moonshot is available across API, desktop, web and self-hosted platforms.

Promptfoo is worth considering for local or self-hosted LLM evaluation: its free Community plan includes 10k red-team probes per month and all LLM evaluation features, model providers and integrations.

PromptGuard offers 20,000 scans a month on its free plan, with one API key, one project and 24-hour log retention; its Team plan is $19 a month.

PyRIT is a free open-source framework for users comfortable with a Python environment and configured AI endpoints. Augustus is another free, Apache 2.0-licensed open-source option, with provider credentials potentially needed for API use. Basilisk is free AGPL-3.0 software distributed as a CLI, desktop app, Docker image or source, for authorized use only.

AgentScan may suit readers who want a web-based agent scanner: its free plan allows five scans per month and covers 185 attack vectors across five categories. Giskard offers a free open-source library for local deployment, including a basic LLM vulnerability scan and basic RAG evaluation report.

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

Verdict

OpenSecureAI Scanner is a sensible choice for developers and AI teams who want accessible text screening, several integration routes and stronger hosted detections behind an API key. Its free tools lower the barrier to trying it, but the free API cap is modest and paid setup requires sales contact. Look elsewhere if your priority is a larger free scan allowance, or if you need Team’s planned seats, SSO or custom rules now.