Three trust-boundary checks
Scan customer messages before model execution, selected documents or chunks before prompt assembly, and proposed tool calls before execution.
Koreshield
Freemium
Koreshield è un livello di sicurezza runtime e di evidenze per i flussi di assistenza basati sull’AI. Controlla gli input dei clienti, il contesto recuperato e le azioni degli strumenti proposte prima che diventino comportamenti affidabili del modello o azioni operative.
Cos'è Koreshield?
Koreshield is a runtime security and evidence layer for AI customer-support applications. It inspects customer-controlled input, retrieved context, and proposed tool actions before they become trusted model context or operational behavior.
Teams can begin in detect mode beside representative traffic, review decisions and evidence, and enable enforcement only after they understand false positives, misses, latency, and fallback behavior. Koreshield complements application authorization and does not replace identity, tenant, approval, or business-rule controls.
Cosa può fare Koreshield?
Detect and enforce modes
Use detect mode to record threats without interrupting traffic, then use enforce mode to stop requests that violate policy when fallback behavior is ready.
Decision evidence
Return and retain operational decision details such as outcome, severity, confidence, indicators, mode, timing, and a request record for review.
Server-side API integration
Create a server-side scan key and call documented endpoints for input, retrieved-context, and proposed-action checks. Examples are provided for JavaScript, Python, and cURL.
Validation before rollout
Test representative benign and adversarial support cases and review misses, false positives, latency, blocked-response behavior, and evidence usefulness before enforcement.
Hosted plan options
Hosted Starter and Growth plans meter protected requests, while Enterprise is scoped for custom volume, deployment, identity, retention, evidence export, and support requirements.
Casi d'uso
“Support chat input screening”
A support application can scan a customer message before it enters the assistant conversation, helping the team identify untrusted instructions or suspicious content at the first workflow boundary.
“RAG and knowledge-base protection”
Teams can scan ticket notes, CRM snippets, documents, or other selected retrieved chunks before prompt assembly to identify indirect prompt injection and false authority claims.
“Pre-execution action review”
An agent workflow can submit a proposed refund, account change, data export, or handoff with its authorization context before the tool call runs.
“Measured production rollout”
A team preparing an AI support workflow can run Koreshield in detect mode beside live traffic, compare decisions with expected behavior, and introduce enforcement with a defined customer and operator fallback.
Domande frequenti
Does Koreshield require replacing the model provider?
No. The application can add a direct scan before the provider call or use a protected proxy route where that fits its architecture.
What does a Koreshield decision contain?
A decision can include whether the request is allowed, detected, or blocked, together with severity, confidence, indicators, mode, timing, and an event record for review.
How should a team start an integration?
Create a server-side scan key, choose one trust boundary, run detect mode against representative traffic, and enforce only after the team understands false positives, misses, latency, and fallback behavior.
Does Koreshield replace a WAF or authorization system?
No. It focuses on AI workflow trust boundaries rather than acting as a general WAF, identity provider, API gateway, or replacement for application authorization.
What is included in the public evaluation?
Eligible new customers can use one seven-day evaluation without a card. It includes 10,000 protected requests, one API key, and a 20-request-per-minute limit.
Informazioni rapide
- Category
- AI security
- Primary users
- Teams operating or preparing AI customer-support workflows
- Trust boundaries
- Customer input, retrieved context, and proposed actions
- Integration
- Server-side API with documented JavaScript, Python, and cURL examples
- Hosted pricing
- Starter £20/month; Growth £99/month; Enterprise custom
- Evaluation
- 7 days, no card, 10,000 protected requests, 1 API key, and 20 requests/minute
Analisi del traffico di Koreshield
I dati sul traffico sono solo a scopo di riferimento.
- Domain Rating
- 15
Alternative a Koreshield
CybeDefend
www.cybedefend.com
CybeDefend è una piattaforma di sicurezza del codice progettata per i flussi di lavoro di programmazione con l’IA. Il livello VibeDefend esamina i prompt degli agenti e i diff, applica le regole del progetto e aziendali, protegge dalle azioni rischiose e riunisce le scansioni di codice, dipendenze, segreti, infrastruttura e CI/CD prima di una pull request.
Agent Plugin Marketplace
www.cosmicjs.com
Un marketplace per installare plugin dei fornitori sull’agente Cosmic responsabile di un’attività. È pensato per i team che utilizzano agenti Cosmic, strumenti MCP e flussi di lavoro correlati a contenuti o operazioni.
Beagle Security
beaglesecurity.com
Test di sicurezza basati sull’IA per app web, API e GraphQL
Pangea
pangea.cloud
Pangea è una piattaforma di sicurezza per applicazioni di IA che aggiunge controlli di protezione a prompt, output, accesso ai dati e logging. Protegge i flussi di lavoro LLM tramite API, SDK, strumenti di IA o gateway API.
ClariLayer
clarilayer.com
ClariLayer è un livello di contesto personale per agenti AI di programmazione e analisi, che li aiuta a conservare definizioni dei dati, note e join tra una sessione e l’altra. Confronta inoltre il contesto salvato con le evidenze del data warehouse o di HubSpot, segnalando eventuali discrepanze come avvertenze.