Feature
core/prompt-injection-shield
Declares that the model requests a gateway forwards are checked for attempts to override the instructions a model was given, before the model is called, at one of two sensitivities: strict refuses more such attempts, and more legitimate requests with them. The check is a probabilistic classifier's verdict: it misses some attacks, reworded, encoded or respelled ones among them, refuses some legitimate requests, and is known to be evadable, so it is one control beside others. It does not judge the model's reply, tool-call arguments or images. A realization either sends the requests through a guard wired to the gateway's guard socket, which checks each one and forwards what it admits to the model, or turns on a check the gateway runs itself. core/gateway/litellm and core/gateway/nginx realize it with core/security/nemo-guardrails as the guard, each halting the build with no guard wired or unless the guard's threshold is the one the sensitivity names. core/gateway/azure-api-management realizes it as Azure's prompt shield, which is on or off, so it keeps standard alone. What each check reads, and what the gateway still serves, is stated on each realization. On a gateway with no realization, attaching it halts the build naming the type.
Herkunft
- Inhalts-Digest
- sha256:f7138e93d2d53f7fbed1ced67aaf82b180b079daed347e5231473ad39cc2adfc
- Veröffentlicht
- 2026-11-10T10:17:17Z
- Signaturidentität
- https://token.actions.githubusercontent.com/https://github.com/aggrega-ai/aggrega-hub/.github/workflows/catalog-publish-sign.yml@refs/heads/main
Signatur
- Offiziellapplication/vnd.dev.sigstore.bundle.v0.3+json
https://token.actions.githubusercontent.com/https://github.com/aggrega-ai/aggrega-hub/.github/workflows/catalog-publish-sign.yml@refs/heads/main
sha256:f1cc347d042fb5403c17380a18db62fa747ac4fa1c283719fe7832e2d38415e0
Referenz zu dieser Version
oci://hub.aggrega.ai/feature/core/prompt-injection-shield:1.0.0- Gilt für
- component.aggrega.ai/category=gateway
- Steht in Konflikt mit
- —
Entwicklerparameter
Werte, die der Entwickler beim Anbinden dieser Funktion festlegt.
Erweitert BaseComponents#/schemas/BaseFeatureParameter
| Name | Typ | Standardwert | Erforderlich | Beschreibung |
|---|---|---|---|---|
| sensitivity | string (standard | strict) | standard | ja | — |
Ausgabevertrag
Werte, die diese Funktion an Konsumenten veröffentlicht.
Keine Ausgabewerte deklariert.
Annotationen
Keine Annotationen deklariert.
Beziehungen
Typisierte Kanten zu und von anderen veröffentlichten Entitäten. Eine Referenz ohne veröffentlichtes Ziel wird als unterbrochene Kante statt als Link dargestellt.
Verwendet
- gilt fürgilt für
component.aggrega.ai/category=gateway
core/gateway/agentgateway v1.0.0 →core/gateway/apisix v1.0.0 →core/gateway/azure-api-management v1.0.0 →core/gateway/cloudflare-ai-gateway v1.0.0 →core/gateway/contour v1.0.0 →core/gateway/envoy-ai-gateway-operator v1.0.0 →core/gateway/envoy-gateway v1.0.0 →core/gateway/higress v1.0.0 →core/gateway/kong v1.0.0 →core/gateway/kong-enterprise v1.0.0 →core/gateway/litellm v1.0.0 →core/gateway/nginx v1.0.0 →core/gateway/traefik-hub v1.0.0 →core/gateway/tyk v1.0.0 →example/gateway/nginx-reviewed v1.0.0 → - $referweitert Schema (values)
BaseComponents#/schemas/BaseFeatureParameter
Verwendet von
implementiert
implementiert
implementiert
implementiert
implementiert
implementiert
implementiert