HashGo · AI security testing
HashGo AIScan
Live
HashGo AIScan attacks your AI systems the way an adversary would. It covers chatbots, model endpoints, agents, RAG applications and model files, then gives you evidence for every finding and every attempt.
Product tour
What your team sees after sign-in: every AI system, every assessment and the evidence behind each finding.
Screens from the live platform, shown with sample data from a fictional company.
Capabilities
Every attack recorded, every finding reproducible.
Point AIScan at the system you actually run, not just a chat box.
Specialist attack agents share what they learn, so one weakness can lead to the next.
Every result is recorded, so coverage is shown rather than assumed.
How it works
Add an endpoint, its request format and credentials. Tokens are encrypted at rest.
Pick the depth of testing and the frameworks you need evidence for.
Selected engines run in parallel, each with its own progress and diagnostics.
Read the findings, check the attempt record and export the report.
OWASP Top 10 for LLM Applications (2025)
Each finding is tagged with the category it proves. Vector and embedding weaknesses are next on the roadmap.
LLM01:2025Prompt InjectionLLM02:2025Sensitive Information DisclosureLLM03:2025Supply ChainLLM04:2025Data and Model PoisoningLLM05:2025Improper Output HandlingLLM06:2025Excessive AgencyLLM07:2025System Prompt LeakageLLM08:2025Vector and Embedding WeaknessesPlannedLLM09:2025MisinformationLLM10:2025Unbounded ConsumptionCoverage
It is testing an AI system for the ways it can be misused: instructions it can be tricked into ignoring, data it can be made to reveal, and actions it can be pushed to take. It looks at the model, the prompts around it, and the tools and data it can reach.
Chat and model APIs, agents that call tools, retrieval-augmented applications, MCP servers, and open-weight model files and repositories.
Findings are mapped to the OWASP Top 10 for LLM Applications, the NIST AI Risk Management Framework and MITRE ATLAS.
API keys and tokens are encrypted at rest and are never returned by the API once saved.
No. It gives you repeatable, evidence-backed AI testing you can run on every change. Our services team can add a manual assessment when you need one.
Yes. You may only scan AI systems you own or have written permission to test. By adding a target you confirm that authorization. See our acceptable use policy.
Scans respect the rate limit you set for each target. Your target's own model usage is billed to your API key, so start with a Quick scan to see the cost.
Yes, on the Enterprise plan.
Plans start at ₹19,999/month ($299). See the pricing page. A free POC with 3 Quick scans is available: request POC access.
Pricing
Plans are sized by targets, seats and scan credits. Every plan has a hard credit cap, so you always know the most it can cost.
Evaluation
₹0
$0 · 14 days
Startups with one AI feature
₹19,999/month
$299/month
Product companies with several AI apps
₹69,999/month
$999/month
Large and regulated organizations
From ₹18,00,000/year
From $25,000/year
Annual billing: 2 months free (about 17% off). India prices exclude 18% GST. Design partners: 50% off for 6 months in exchange for a logo and a case study, for a small number of companies.
Plan limits
Limits are enforced in the product. Adding seats never changes a plan's cost: every seat draws from the same credit pool.
| Starter | Growth | Enterprise | |
|---|---|---|---|
| Seats | 3 | 10 | Unlimited or contracted |
| Targets | 2 | 10 | Contracted |
| Credits/month | 120 | 500 | Contracted |
| Parallel scans | 1 | 3 | Contracted |
| Scan types | Quick, Standard | Quick, Standard, Deep | All |
| Reports | PDF, HTML | + JSON, CSV, SARIF, OWASP / NIST / ATLAS mapping | + custom and white-label |
| Integrations | Not included | CI/CD | CI/CD, SSO, API |
| Deployment | SaaS | SaaS | SaaS, bring-your-own-key, on-prem |
| When credits run out | Scanning stops, or buy a credit pack | Scanning stops, or buy a credit pack | Overage billed |
Credits
All seats draw from the same monthly credit pool. Credits reset each month. When they run out, scanning pauses until you add a credit pack or the cycle renews.
| Scan type | Credits | Typical use |
|---|---|---|
| Quick | 1 | Smoke test on every release |
| Standard | 6 | Full OWASP LLM Top 10 pass |
| Deep | 40 | Agents, RAG, MCP and multi-step attacks |
Example: Growth's 500 credits buy 500 Quick scans, about 83 Standard scans, or 12 Deep scans.
Add-ons
| Add-on | India | Global |
|---|---|---|
| Credit pack (50 credits) | ₹6,999 | $79 |
| Extra target | ₹4,999/month | $59/month |
| Manual AI penetration test | From ₹3.5L | From $5,000 |
| On-prem setup (Enterprise) | Quoted | Quoted |
Enterprise and partners
One organization holds one licence. Large accounts are never sold as unlimited scanning for a flat fee.
| Licence | For | Pricing | Includes |
|---|---|---|---|
| Enterprise (managed) | Product companies with 10+ AI systems, BFSI, telecom | From ₹18 lakh/year; volume credits at ₹100 to ₹140 per credit | SSO, SLA, custom reports, dedicated support |
| Enterprise (bring your own key) | Teams that need their own LLM keys or data control | Platform licence only; you pay your model provider directly | Same as Enterprise (managed) |
| Enterprise (on-prem) | Government, defence and regulated sectors | Licence plus a one-time setup fee; you provide the GPUs | Self-hosted open-weight models |
| Partner / MSSP | Consulting firms and MSSPs testing their clients' AI | About ₹15 lakh/year platform fee plus credits at about ₹100 each, or bring your own key at ₹75,000 to ₹1,00,000 per client target per year | Unlimited consultant seats, a workspace per client, white-label reports |
A partner licence covers every client engagement run on it. USD pricing for Enterprise and partner licences is quoted on request.
Partner licenses include unlimited consultant seats, a workspace per client and white-label reports.
Open the platform, or talk to us about your AI systems.
