Overview

OpenSecureAI Scanner screens untrusted text for prompt-injection and related patterns, with browser, developer-tool and hosted API routes. It suits teams adding a focused check to AI application workflows, though its monthly request caps and sales-led paid setup may constrain production use.

Its scanPrompt library returns a score from 0 to 100, a risk level and per-rule findings. That makes results more actionable than a bare pass-or-fail signal, but the scanner's stated scope is text screening rather than a complete assessment of AI-system security.

Key features

Teams can integrate 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 useful fit for Node applications and build workflows. The maker describes its in-browser tools and npm packages as free and open. Anonymous API access uses the basic engine and is rate-limited by IP.

Authenticated hosted API calls add coverage for obfuscation and encoding evasions, indirect injection, tool abuse, multilingual overrides and de-obfuscation. These detections broaden screening beyond straightforward attacks, but the hosted engine requires an API key. The Free plan includes 2,000 API requests per month and 30 requests per minute per key.

The LLM Gateway can forward prompts to a selected OpenAI, Anthropic, xAI or Groq provider and model, then scan the response. That gives teams a route to connect screening with model calls, while keeping provider choice within those four services. Documentation says authenticated scans save a summary to the dashboard but never store raw prompt text; provider keys for Gateway calls are neither stored nor logged.

The scanner supports prompt-injection, jailbreak, data-leakage and unsafe-output tests. The maker also describes its broader platform as addressing threats including data poisoning and model theft, but the scanner's specific detection scope is the text-pattern set described above. The contact page says vulnerability reports receive a response within 48 hours.

Pricing

The Free plan is billed at $0/month and includes 2,000 API requests per month, 30 requests per minute per key, in-browser tools, npm packages and access to the hosted advanced engine with an API key. It is a sensible starting point for learning, evaluation or modest usage; teams with sustained traffic will need to account for both caps.

Pro costs 49.00 USD per 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. It fits a team that needs materially more throughput and Gateway access, though the quota remains finite.

Team has custom pricing and is billed Custom. It 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 rather than included capabilities. Paid checkout is not self-serve: customers must contact sales to be set up, a meaningful hurdle for buyers seeking immediate, predictable provisioning.

Platforms

OpenSecureAI Scanner supports API, Linux, macOS, web and Windows. The npm package's Node 18+ requirement gives developers a clear runtime target; the listed platform range also accommodates browser access and API-based integration.

Who it's for

AI application teams, agent and MCP developers, security and compliance reviewers, learners and red-teamers are the maker's stated audiences. Developers seeking an embeddable text check have multiple integration paths, while security reviewers may value per-rule findings and the hosted engine's broader evasion detections. It is less compelling for buyers who need a broad, independently established security program or self-serve paid procurement.

Pros and cons

Pros: Four integration formats and a dependency-free Node package make it practical to add screening to applications and workflows.
Pros: The scanPrompt score, risk level and per-rule findings provide more context for acting on a flagged input.
Pros: The hosted engine adds checks for indirect injection, tool abuse and obfuscation, while documented handling avoids retaining raw prompt text.
Cons: Free API use is capped at 2,000 requests monthly and 30 per minute per key, which can limit regular traffic.
Cons: Pro still has a 50,000-request monthly ceiling, and paid access requires contacting sales rather than checking out directly.
Cons: Team seats, SSO, custom rules and an SLA are planned, so organizations needing those terms cannot treat them as current plan benefits.

Alternatives

Choose Promptfoo if you want a free community tier with 10k red-team probes per month, broad LLM evaluation features, model-provider integrations and local or self-hosted runs. PromptGuard is worth comparing when its free allowance of 20,000 scans a month, one API key and one project better match your expected volume; its Team plan is 19.00 USD per month.

AIRTA Red Team is a free, open-source option with no license fee or subscription, but it requires you to bring your own LLM API key. PyRIT is another free open-source framework if you have a Python environment and configured AI endpoints. Augustus is a free Apache 2.0 option for Linux, macOS or Windows, with provider credentials potentially needed for API use; Basilisk is a free AGPL-3.0 choice for authorized use, distributed as a CLI, desktop app, Docker image or source.

Project Moonshot is a free option. Consider F5 BIG-IP APM if its paid licensing, free trial and broad platform support better fit your requirements. For broader discovery, see AI Security Testing Tools and AI Red Teaming Tools.

Verdict

OpenSecureAI Scanner is a strong fit for developers and AI security teams that want focused text screening in a Node workflow or through a hosted API, particularly when its advanced evasion checks and Gateway matter. Choose it for that integration mix and per-rule output; look elsewhere if your workload exceeds its quotas, you need self-serve paid setup, or you require Team features that remain planned.

	OpenSecureAI Scanner	SENTINEL RED
Free plan	Yes
Paid from	$49/mo
Platforms	api, Linux, macOS, Web, Windows	api, Linux, self-hosted, Web
Free plan	Yes
Paid from	49 /mo
Prompt injection tests	Yes	Yes
Jailbreak tests	Yes	Yes
Data leakage tests	Yes	Yes
Unsafe output tests	Yes	Yes
Deployment mode	both	self_hosted
Custom test cases		Yes

OpenSecureAI Scanner vs SENTINEL RED

OpenSecureAI Scanner

SENTINEL RED