OpenSecureAI Scanner

Overview

OpenSecureAI Scanner screens untrusted text for prompt injection and related risks, with options for browser-based checks, developer integrations and a hosted API. It suits AI application developers and security reviewers who need a focused screening layer; its key trade-off is a small free API allowance and sales-led setup for paid plans.

The scanPrompt library returns a score from 0 to 100, a risk level and findings for individual rules. Its scope includes jailbreaks, system-prompt leaks and data-exfiltration patterns alongside prompt injection. That focus makes it useful for checking text in an AI workflow, but it should not be mistaken for comprehensive protection against every threat to an AI system.

Key features

Developers 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, making it a practical option for Node applications and build workflows. In-browser tools and npm packages are free and open. Anonymous API access uses the basic engine and is rate-limited by IP, so it is best for trying the service or modest use rather than relying on higher-volume or advanced checks.

Authenticated hosted API calls add detections for obfuscation and encoding evasions, indirect injection, tool abuse, multilingual overrides and de-obfuscation. These checks broaden coverage beyond direct, plainly worded attacks, but require an API key. The LLM Gateway can forward prompts to a selected OpenAI, Anthropic, xAI or Groq provider and scan the response, a useful fit for teams already using one of those providers.

Authenticated scans save a summary to the dashboard without storing raw prompt text. Gateway provider keys are not stored or logged. The company says it responds to vulnerability reports within 48 hours, a concrete disclosure commitment for security-conscious adopters.

Pricing

The Free plan is billed $0/month and includes 2,000 API requests/month, 30 requests/minute per key, in-browser tools and npm packages, plus the hosted advanced engine with an API key. It is a sensible starting point for learning, prototypes and low-volume evaluation, but the request cap and rate limit can constrain production use.

Pro costs $49 a month (billed $49/month). It raises the allowance to 50,000 API requests/month and 120 requests/minute per key, and includes hosted AI remediation, LLM Gateway completions and priority email support. It is the clearest fit for an individual developer or smaller team that needs more capacity and hosted features, though paid checkout is not self-serve: customers must contact sales to be set up.

Team has custom pricing and includes 250,000 API requests/month and 300 requests/minute per key. Team seats and SSO, as well as custom rules and an SLA, are planned rather than current inclusions, so the stated capacity may suit larger workloads but should not be read as a present promise of those team controls.

Platforms

OpenSecureAI Scanner is available through API, Linux, macOS, web and Windows. Its npm package and command-line options suit developer workflows, while browser tools provide a lower-friction way to try checks.

Who it's for

AI application teams, agent and MCP developers, security and compliance reviewers, learners and red-teamers are the intended audiences. Developers integrating text checks into Node projects will value the dependency-free package and multiple interfaces. Teams seeking broad security coverage beyond text scanning, or a paid plan they can activate without sales contact, should look elsewhere.

Pros and cons

Pros

• Several integration paths: npm, CLI, GitHub Action and REST API let developers place checks in applications or build workflows.
• Advanced hosted detections: Authenticated calls cover indirect injection, tool abuse and obfuscation-related evasions beyond the basic engine.
• Privacy-conscious handling: Authenticated scans retain a summary rather than raw prompt text, and Gateway provider keys are not stored or logged.
• Free ways to start: Browser tools and npm packages are free and open, with a $0/month API plan for limited hosted use.

Cons

• Free API capacity is modest: 2,000 requests/month and 30 requests/minute per key may be insufficient for sustained application traffic.
• Paid setup requires sales: Pro is not self-serve, adding friction for buyers who want to upgrade immediately.
• Team controls are planned: Seats, SSO, custom rules and SLA are not current Team inclusions.
• Focused scope: The scanner checks untrusted text patterns, not every security risk affecting AI systems.

Alternatives

PromptGuard is worth considering when a higher free scan allowance matters: its Free plan includes 20,000 scans a month, one API key, one project and 24-hour log retention. Promptfoo is a stronger fit for broader LLM evaluation and red-team probing, with a Community plan that includes 10k red-team probes/month and local or self-hosted use. Project Moonshot is a free alternative for readers who want its available API, desktop and self-hosted platform options.

AIRTA Red Team is a free, open-source option for users prepared to bring their own LLM API key. PyRIT is a free open-source framework for readers comfortable with a Python environment and configured AI endpoints. Augustus is a free Apache 2.0 option available for desktop operating systems and self-hosted use. Basilisk is another free open-source choice, with CLI, desktop, Docker or source distribution and authorized use only. F5 BIG-IP APM is a paid alternative with a free trial for readers evaluating an access-management product rather than a focused text scanner.

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

Verdict

OpenSecureAI Scanner is a good choice for developers and AI security teams that want to add prompt-risk checks through a lightweight package or API, especially when authenticated hosted detections and the Gateway fit their workflow. Its free tools make evaluation accessible, but the capped API plan and sales-led paid setup are real constraints; choose another option if you need broad security coverage, higher free volume or self-serve paid onboarding.