Skip to content
SPECIFICTION
Get listed

OpenSecureAI Scanner

opensecureai.com

From $49/mo Free plan Open source WebWindowsmacOSLinuxAPISelf-hosted
Visit opensecureai.com
Spec score 9.0 #2 of 29 in AI Security Testing Tools

What it is

OpenSecureAI Scanner checks untrusted text for patterns that may indicate prompt injection, jailbreaks, system-prompt leaks, or data exfiltration. Its scanPrompt library API returns a 0–100 score, a risk level, and findings for individual rules. Developers can access it as an npm package, CLI, GitHub Action, or REST API; the package targets Node 18+ and has zero runtime dependencies. Authenticated hosted API calls add detections for obfuscation and encoding evasions, indirect injection, tool abuse, multilingual overrides, and de-obfuscation. The LLM Gateway can route prompts to a selected OpenAI, Anthropic, xAI, or Groq provider and scan the response. Documentation says authenticated scans save a summary to the dashboard but do not store raw prompt text; gateway provider keys are not stored or logged. Free access includes in-browser tools and npm packages, while the anonymous API uses the basic engine with IP rate limiting. The Free plan lists 2,000 API requests per month. Pro costs $49 a month, but paid checkout is not self-serve and requires contacting sales.

Spec sheet

What it does
OpenSecureAI is an AI and generative-AI security platform for detecting prompt injection, data poisoning, model theft and related threats.Read 15 Oct 2026 · opensecureai.com
Purpose
OpenSecureAI describes its platform as tools, threat intelligence, and learning resources to protect AI systems from prompt injection, data poisoning, model theft, and emerging GenAI threats.Read 2 Oct 2026 · opensecureai.com
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.Read 2 Oct 2026 · opensecureai.com
API
The public REST API exposes scan, unified analysis, agent-guard, gateway, events and threat-feed endpoints.Read 15 Oct 2026 · opensecureai.com
Integrations
The LLM Gateway can forward prompts to a selected OpenAI, Anthropic, xAI, or Groq provider/model and scan the response.Read 2 Oct 2026 · opensecureai.com
Privacy
Browser tools process prompts locally, the public scan API does not persist submitted text, and authenticated scan history stores summaries rather than raw prompts.Read 15 Oct 2026 · opensecureai.com
Headquarters
The company describes itself as global and remote-first rather than listing a physical headquarters.Read 15 Oct 2026 · opensecureai.com
Founded
2026Read 28 Sep 2026 · opensecureai.com
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.Read 15 Oct 2026 · opensecureai.com
CLI and CI
The scanner and firewall packages include command-line interfaces, and the scanner provides a GitHub Action for pull-request gating.Read 15 Oct 2026 · opensecureai.com
Company founding
OpenSecureAI states that it was founded in 2026 and launched its prompt-injection scanner and platform during 2026.Read 15 Oct 2026 · opensecureai.com
Company history
The About page says OpenSecureAI was founded in 2026 and is global and remote-first.Read 2 Oct 2026 · opensecureai.com
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.Read 2 Oct 2026 · opensecureai.com
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.Read 15 Oct 2026 · opensecureai.com
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.Read 2 Oct 2026 · opensecureai.com
Gateway integrations
The gateway names OpenAI, Anthropic, xAI and Groq as supported providers and accepts customer-supplied keys.Read 15 Oct 2026 · opensecureai.com
Hosted engine
Authenticated hosted API calls add private detections for obfuscation and encoding evasions, indirect injection, tool abuse, multilingual overrides, and de-obfuscation.Read 2 Oct 2026 · opensecureai.com
Independent domain assessment
ScamAdviser describes opensecureai.com as very likely safe, citing valid SSL and DNSFilter safety signals.Read 15 Oct 2026 · scamadviser.com
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.Read 15 Oct 2026 · npmjs.com
Independent reputation score
Gridinsoft reports a 72/100 trust score for opensecureai.com and says no major malware or phishing detections were found.Read 15 Oct 2026 · fr.gridinsoft.com
Key handling
The docs state that LLM Gateway provider keys are never stored or logged.Read 2 Oct 2026 · opensecureai.com
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.Read 15 Oct 2026 · opensecureai.com
Limit: account and enterprise controls
Team seats, SSO, custom rules and SLA support are marked planned, and paid checkout currently requires contacting sales.Read 15 Oct 2026 · opensecureai.com
Limit: domain transparency
ScamAdviser flags free registration email addresses and low Tranco traffic rank as negative signals.Read 15 Oct 2026 · scamadviser.com
Limit: independent verification
Gridinsoft characterizes the domain as reliable but still requiring verification rather than fully validated.Read 15 Oct 2026 · fr.gridinsoft.com
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.Read 15 Oct 2026 · opensecureai.com
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.Read 15 Oct 2026 · opensecureai.com
Offline use
The basic scanner engine runs locally in the browser, CLI or GitHub Action; authenticated API keys add hosted detections.Read 15 Oct 2026 · opensecureai.com
Plan availability
The pricing page says paid checkout is not self-serve yet and customers should contact sales to be set up.Read 2 Oct 2026 · opensecureai.com
Praise: privacy
The independent domain checks highlight an active SSL certificate and absence of major malware or phishing detections.Read 15 Oct 2026 · fr.gridinsoft.com
Prompt Firewall
Prompt Firewall applies configurable allow, flag or block decisions, blocking injection and secrets while redacting and flagging PII.Read 15 Oct 2026 · opensecureai.com
Red-team playground
The browser playground offers five local capture-the-flag challenges covering direct overrides, filter bypasses, role-play jailbreaks, indirect injection and encoding smuggling.Read 15 Oct 2026 · opensecureai.com
Scanner detection
The scanner uses dependency-free heuristics for prompt injection, jailbreaks, system-prompt leakage and data-exfiltration patterns.Read 15 Oct 2026 · opensecureai.com
Scanner outputs
The scanPrompt library API returns a 0–100 score, a risk level, and per-rule findings.Read 2 Oct 2026 · opensecureai.com
SDKs and packages
Public TypeScript npm packages are offered for scanner, firewall and agent-guard, each described as dependency-free or dependency-light.Read 15 Oct 2026 · opensecureai.com
Secret and PII coverage
The analyzer identifies API keys, tokens, private keys, email addresses, Social Security numbers and payment cards and provides masked output.Read 15 Oct 2026 · opensecureai.com
Security disclosures
The contact page says the company responds to vulnerability reports within 48 hours.Read 2 Oct 2026 · opensecureai.com
Security limitation
The terms warn that heuristic scans can produce false positives or miss issues and are not a security guarantee.Read 15 Oct 2026 · opensecureai.com
System requirements
The scanner package targets Node.js 18 or newer, uses ESM and TypeScript types, and has zero runtime dependencies.Read 15 Oct 2026 · opensecureai.com
System-prompt audit
The system-prompt audit grades secret isolation, injection resistance and least-privilege practices on an A-to-F scale with prioritized fixes.Read 15 Oct 2026 · opensecureai.com
Unified analysis
Analyze combines prompt-injection detection, secrets and PII scanning, and optional system-prompt auditing in one browser workflow.Read 15 Oct 2026 · opensecureai.com

Plans and prices

Free Free $0/month 2,000 API requests/month · 30 requests/minute per key · browser tools and npm packages · hosted advanced engine · scan history · LLM Gateway BYOK · BYOK AI remediation Read 15 Oct 2026 · opensecureai.com
Pro $49 a month $49/month 50,000 API requests/month · 120 requests/minute per key · hosted AI remediation · hosted LLM Gateway completions · priority email support Read 15 Oct 2026 · opensecureai.com
Team Priced on request Custom 250,000 API requests/month · 300 requests/minute per key · team seats and SSO planned · custom rules and SLA planned Read 15 Oct 2026 · opensecureai.com

Every OpenSecureAI Scanner plan and price →

Strong points and limits

Strong points

  • Scans for injection, jailbreak, prompt leaks, and data exfiltration.
  • API returns a score, risk level, and rule findings.
  • Available as an npm package, CLI, GitHub Action, and REST API.
  • Authenticated scans do not store raw prompt text.

Limits

  • Pro costs $49 a month.
  • Paid checkout requires contacting sales.
  • Anonymous API uses the basic engine and IP rate limiting.

Who it suits

It suits AI application teams, agent and MCP developers, security and compliance reviewers, learners, and red-teamers. Developers can use the scanner through a package, CLI, GitHub Action, or REST API.

OpenSecureAI Scanner in depth

Read the full write-up

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 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. 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 a 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.

Verdict

OpenSecureAI Scanner combines text scanning with a hosted engine, developer interfaces, and an LLM Gateway. Check the plan limits and contact-sales requirement before relying on paid access.

Where Specifiction places it

Alternatives to OpenSecureAI ScannerAll alternatives →