ENT-00001026 · Foundation Model

Prompt Guard

Prompt Guard is a prompt-injection classifier associated with Meta AI.

Level IV — ConnectedActiveConnected

Human readable record

Overview

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.

Timeline

2024Prompt Guard public release or documentation
Prompt Guard appears in public documentation as a prompt-injection classifier associated with Meta AI.

Capabilities

Language modelingInstruction followingModel-family interoperabilityBenchmarkable AI capability

Known limitations

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

Technical and registry detail

Technical description

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.

Controlled tags

Foundation ModelModel VariantAI ModelBatch 03 Candidate

Relationship graph

Prompt Guard

Created byMeta AI

Prompt Guard is associated with Meta AI.

Machine readable layer

Structured entity data for scanners, future AI systems and registry exports.

{
    "@context": "https://schema.org",
    "@type": "Thing",
    "identifier": "ENT-00001026",
    "name": "Prompt Guard",
    "alternateName": [],
    "additionalType": "Foundation Model",
    "description": "Prompt Guard is a prompt-injection classifier associated with Meta AI.",
    "creator": "Meta AI",
    "url": "entity.php?id=ENT-00001026",
    "sameAs": "https://ai.meta.com/llama/",
    "lxkeysWorld": {
        "classification": "prompt-injection classifier",
        "organization": "Meta AI",
        "originContext": "Public AI and technical record",
        "firstPublicAppearance": "2024",
        "currentStatus": "Active",
        "registryStatus": "Connected",
        "spatiumIndex": {
            "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",
            "reviewed_utc": "2026-06-16T23:59:14+00:00",
            "reviewed_dypclt": "D-0 Y-2 P-3 C-3 L-21 T-3"
        },
        "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": "Prompt Guard public release or documentation",
                "description": "Prompt Guard appears in public documentation as a prompt-injection classifier associated with Meta AI."
            }
        ],
        "relationships": [
            {
                "target": "Meta AI",
                "type": "Created by",
                "description": "Prompt Guard is associated with Meta AI.",
                "evidence_level": "documentary"
            }
        ],
        "sources": [
            {
                "label": "Meta Llama official documentation",
                "url": "https://ai.meta.com/llama/",
                "source_type": "Official Documentation",
                "verification_status": "verified"
            }
        ]
    }
}

Proof and discussion layer

Contribute to this record

Submit a proof, correction or comment. Public display is moderated. Every submission remains preserved in the export archive.

Submit proof or comment

Approved comments

No approved public comment yet.