Prompt Guard
ENT-00001026 · Modèle IA

Prompt Guard

Prompt Guard is a AI model associated with Meta AI, classified in LXKeys.world as Safety Model.

Niveau IV ConnectéActifDocumenté
Fiche publique

Vue d’ensemble

Prompt Guard is a foundation-model entity associated with Meta AI. The record documents the model inside the prompt-injection classifier family, focusing on its release context, modality, intended capabilities, source lineage and relationship to adjacent model families.

Chronologie

  1. 2024Initial model publication or release

    Prompt Guard entered the documented public record in 2024. This event is retained at the precision supported by the Entry’s reviewed source history.

Capacités

Language modelingInstruction followingModel-family interoperabilityBenchmarkable AI capability

Limites connues

Capabilities vary by checkpoint, deployment configuration and provider policy.The record documents public model identity, not private training details.
Détail technique et structuré

Description technique

Technical model record for Prompt Guard. The structured layer captures provider, model family, release period, capabilities, limitations, source anchors and graph relations to Meta AI, related assistants, evaluation benchmarks and deployment environments.

Tags contrôlés

Foundation ModelModel VariantAI ModelBatch 03 Candidate
Graphe relationnel

Prompt Guard

Ouvrir dans le graphe complet
Prompt Guard
Créé parSortante
Meta AI

Prompt Guard is associated with Meta AI.

Couche lisible par machine

Données structurées de l’entrée pour les outils humains, les systèmes IA et les clients machine.

{
    "@context": [
        "https://schema.org",
        {
            "lxw": "https://lxkeys.world/schema/"
        }
    ],
    "@type": "Thing",
    "identifier": "ENT-00001026",
    "name": "Prompt Guard",
    "alternateName": [],
    "additionalType": {
        "category": "Models",
        "type": "AI Model",
        "subtype": "",
        "lxkeysEntity": false
    },
    "description": "Prompt Guard is a AI model associated with Meta AI, classified in LXKeys.world as Safety Model.",
    "creator": "Meta AI",
    "url": "https://lxkeys.world/entry.php?id=ENT-00001026&lang=fr",
    "sameAs": "https://ai.meta.com/llama/",
    "image": "https://lxkeys.world/uploads/entity-images/ENT-00001026.png",
    "lxkeysWorld": {
        "worldId": "ENT-00001026",
        "kind": "Models",
        "type": "AI Model",
        "subtype": "",
        "classification": "Safety Model",
        "organization": "Meta AI",
        "originContext": "Public AI and technical record",
        "firstPublicAppearance": "2024",
        "currentStatus": "Active",
        "documentationStatus": "Documented",
        "documentationIndex": {
            "total": 74,
            "documentation": 25,
            "evidence": 13,
            "structure": 25,
            "relationships": 11,
            "level": "Level IV Connected"
        },
        "lxCalendarium": {
            "start_date_utc": "2023-04-01",
            "created_utc": "2026-06-16T23:59:14+00:00",
            "created_dypclt": "D-0 Y-2 P-3 C-3 L-21 T-3",
            "updated_utc": "2026-06-16T23:59:14+00:00",
            "updated_dypclt": "D-0 Y-2 P-3 C-3 L-21 T-3"
        },
        "facts": [],
        "capabilities": [
            "Language modeling",
            "Instruction following",
            "Model-family interoperability",
            "Benchmarkable AI capability"
        ],
        "limitations": [
            "Capabilities vary by checkpoint, deployment configuration and provider policy.",
            "The record documents public model identity, not private training details."
        ],
        "tags": [
            "Foundation Model",
            "Model Variant",
            "AI Model",
            "Batch 03 Candidate"
        ],
        "timeline": [
            {
                "date": "2024",
                "title": "Initial model publication or release",
                "description": "Prompt Guard entered the documented public record in 2024. This event is retained at the precision supported by the Entry’s reviewed source history.",
                "source_url": "https://ai.meta.com/llama/",
                "verification_status": "source_backed_official"
            }
        ],
        "relationships": [
            {
                "target": "Meta AI",
                "type": "Created by",
                "description": "Prompt Guard is associated with Meta AI.",
                "evidence_level": "documentary",
                "target_id": "ENT-00000033"
            }
        ],
        "sources": [
            {
                "label": "Meta Llama official documentation",
                "url": "https://ai.meta.com/llama/",
                "source_type": "Official Documentation",
                "verification_status": "verified",
                "authority": "OFFICIAL",
                "role": "primary",
                "update_enabled": true,
                "authority_basis": "curated-corpus-refresh-2026-09-08"
            }
        ],
        "canonical": [],
        "imageMeta": {
            "path": "uploads/entity-images/ENT-00001026.png",
            "sha256": "9a1d256da80746ebe8e3cdb9ee5df3f9d967b852087338a18769cdc9b0fb3b7e",
            "width": 512,
            "height": 512,
            "mime": "image/png",
            "provenance_status": "PROVENANCE_UNCONFIRMED",
            "review_status": "preserved_pending_official_verification",
            "legacy_provenance_status": "legacy_unverified",
            "source_type": "historical",
            "source_label": "LXKeys.world historical media corpus",
            "metadata_namespace": "urn:lxkeys:xmp:1.0",
            "metadata_embedded": true,
            "metadata_verified": true,
            "asset_id": "LXW-IMG-ENT-00001026-9A1D256DA807",
            "processing_id": "LXP-20260908-0FD84D23A5E6",
            "processed_at_utc": "2026-09-08T18:00:00Z",
            "dypclt": "D-0 Y-2 P-4 C-4 L-33 T-6",
            "rights_holder": "",
            "rights_policy": "PROVENANCE_REVIEW_REQUIRED",
            "original_sha256": "9a1d256da80746ebe8e3cdb9ee5df3f9d967b852087338a18769cdc9b0fb3b7e",
            "processed_sha256": "6a3f3dea958f2ef6b62dd8aea4b36bba356efdc9763efb62e5cd324bb8328072"
        }
    }
}
Preuves

Contribuer à cette entrée

Soumettez une source, une correction ou un commentaire. Les modifications publiques restent modérées.

Soumettre une preuve ou un commentaire

Commentaires approuvés

Aucun commentaire public approuvé pour le moment.