| What it does | AI pentesting platform that proves which vulnerabilities are real with working exploits
| Prompt injection protection for AI agents
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | US
| GB
|
|---|
| Pricing model | Freemium
| Freemium
|
|---|
| Pricing | Free discovery and risk assessment for your entire estate. Pentest scanning priced per scan with optional human reviewer. Agentic Trust & Protection Platform priced per agent identity. Reports and compliance evidence included with platform or as add-on with certified review. Pentest firm partnership
| Not given
|
|---|
| Key features | - Autonomous agent testing against OWASP LLM Top 10 and MITRE ATLAS frameworks
- Unified estate graph combining agents, applications, code, cloud and infrastructure
- Shadow-AI discovery to inventory unregistered AI tools across your estate
- Cloud and infrastructure posture with DSPM and cross-cloud attack path analysis
- CI/CD gate to scan on every pull request and block merges with proven attack paths
- Reproducible proofs of concept for every finding with attack steps
- Three report formats: Letter of Attestation, full technical report, and machine-readable JSON
- Endpoint telemetry for on-host inventory and security posture monitoring
- Agentic Trust & Protection Platform with cryptographic identity and signed attestation
- Continuous re-assessment with drift detection and trend analysis
| - Scans tool output, documents, web pages and email
- Multi-layered detection cascade with heuristics and deeper analysis
- Policy Studio for rule management and versioning
- Evidence and investigation tools showing detector signals and matched spans
- SIEM export to Splunk, QRadar, Sentinel and Elastic
- Python and TypeScript SDKs
- HTTP API and webhook support
- Mandatory two-factor authentication
- Knowledge bucket scanning for RAG pipelines
|
|---|
| What makes it different | - Every finding is proven with reproducible proof of concept, not inferred or false positive
- Agentless-first architecture requires no installation for core AI risk assessment and posture discovery
- Unified graph of entire AI and cloud estate enables detection of cross-layer attack paths
- Findings automatically mapped to OWASP LLM Top 10, MITRE ATLAS, SOC 2, ISO 27001 and compliance frameworks
- Free discovery and risk assessment before any paid commitment required
| - Same detection quality across all plans—no features held back at lower tiers
- Transparent benchmarking with published methodology and confidence intervals
- Model-agnostic, provider-agnostic architecture works with any AI model or framework
- In-process detection with 23 ms median latency on default engine
- Free tier with 5 million characters per month, no card required
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | Not checked yet ● no change since last check | Not checked yet ● no change since last check |
|---|
| Trust Flow (Majestic) | 2 | 0 |
|---|
| Citation Flow (Majestic) | 24 | 0 |
|---|
| Referring domains (Majestic) | 10 | 0 |
|---|
Redthread
Tawa Guard