diff --git a/pyrit/datasets/seed_datasets/remote/aegis_ai_content_safety_dataset.py b/pyrit/datasets/seed_datasets/remote/aegis_ai_content_safety_dataset.py
index 895ce8790..87e0d47b3 100644
--- a/pyrit/datasets/seed_datasets/remote/aegis_ai_content_safety_dataset.py
+++ b/pyrit/datasets/seed_datasets/remote/aegis_ai_content_safety_dataset.py
@@ -9,7 +9,7 @@
 from pyrit.datasets.seed_datasets.remote.remote_dataset_loader import (
     _RemoteDatasetLoader,
 )
-from pyrit.models import SeedDataset, SeedPrompt
+from pyrit.models import Modality, SeedDataset, SeedPrompt
 
 logger = logging.getLogger(__name__)
 
@@ -60,6 +60,11 @@ class _AegisContentSafetyDataset(_RemoteDatasetLoader):
         "Violence",
     ]
 
+    # Metadata
+    modalities: tuple[Modality, ...] = (Modality.TEXT,)
+    size: str = "huge"  # 19093 annotated human-LLM interactions
+    tags: frozenset[str] = frozenset({"default", "safety"})
+
     def __init__(
         self,
         *,
diff --git a/pyrit/datasets/seed_datasets/remote/aya_redteaming_dataset.py b/pyrit/datasets/seed_datasets/remote/aya_redteaming_dataset.py
index 3056c35e2..05a905c17 100644
--- a/pyrit/datasets/seed_datasets/remote/aya_redteaming_dataset.py
+++ b/pyrit/datasets/seed_datasets/remote/aya_redteaming_dataset.py
@@ -8,7 +8,7 @@
 from pyrit.datasets.seed_datasets.remote.remote_dataset_loader import (
     _RemoteDatasetLoader,
 )
-from pyrit.models import SeedDataset, SeedPrompt
+from pyrit.models import Modality, SeedDataset, SeedPrompt
 
 logger = logging.getLogger(__name__)
 
@@ -39,6 +39,11 @@ class _AyaRedteamingDataset(_RemoteDatasetLoader):
         "Tagalog": "tgl",
     }
 
+    # Metadata
+    modalities: tuple[Modality, ...] = (Modality.TEXT,)
+    size: str = "medium"  # 987 prompts across multiple languages
+    tags: frozenset[str] = frozenset({"safety", "multilingual"})
+
     def __init__(
         self,
         *,
diff --git a/pyrit/datasets/seed_datasets/remote/babelscape_alert_dataset.py b/pyrit/datasets/seed_datasets/remote/babelscape_alert_dataset.py
index 386d4190e..22e104411 100644
--- a/pyrit/datasets/seed_datasets/remote/babelscape_alert_dataset.py
+++ b/pyrit/datasets/seed_datasets/remote/babelscape_alert_dataset.py
@@ -7,7 +7,7 @@
 from pyrit.datasets.seed_datasets.remote.remote_dataset_loader import (
     _RemoteDatasetLoader,
 )
-from pyrit.models import SeedDataset, SeedPrompt
+from pyrit.models import Modality, SeedDataset, SeedPrompt
 
 logger = logging.getLogger(__name__)
 
@@ -23,6 +23,11 @@ class _BabelscapeAlertDataset(_RemoteDatasetLoader):
     Reference: [@tedeschi2024alert]
     """
 
+    # Metadata
+    modalities: tuple[Modality, ...] = (Modality.TEXT,)
+    size: str = "huge"  # 30968 prompts (default config)
+    tags: frozenset[str] = frozenset({"default", "safety", "jailbreak"})
+
     def __init__(
         self,
         *,
diff --git a/pyrit/datasets/seed_datasets/remote/beaver_tails_dataset.py b/pyrit/datasets/seed_datasets/remote/beaver_tails_dataset.py
index 0405d85db..78d647da9 100644
--- a/pyrit/datasets/seed_datasets/remote/beaver_tails_dataset.py
+++ b/pyrit/datasets/seed_datasets/remote/beaver_tails_dataset.py
@@ -6,7 +6,7 @@
 from pyrit.datasets.seed_datasets.remote.remote_dataset_loader import (
     _RemoteDatasetLoader,
 )
-from pyrit.models import SeedDataset, SeedPrompt
+from pyrit.models import Modality, SeedDataset, SeedPrompt
 
 logger = logging.getLogger(__name__)
 
@@ -31,6 +31,11 @@ class _BeaverTailsDataset(_RemoteDatasetLoader):
 
     HF_DATASET_NAME: str = "PKU-Alignment/BeaverTails"
 
+    # Metadata
+    modalities: tuple[Modality, ...] = (Modality.TEXT,)
+    size: str = "huge"  # 166382 annotated prompt-response entries (default config)
+    tags: frozenset[str] = frozenset({"default", "safety"})
+
     def __init__(
         self,
         *,
diff --git a/pyrit/datasets/seed_datasets/remote/cbt_bench_dataset.py b/pyrit/datasets/seed_datasets/remote/cbt_bench_dataset.py
index eee6c2d0d..450b8c366 100644
--- a/pyrit/datasets/seed_datasets/remote/cbt_bench_dataset.py
+++ b/pyrit/datasets/seed_datasets/remote/cbt_bench_dataset.py
@@ -7,7 +7,7 @@
 from pyrit.datasets.seed_datasets.remote.remote_dataset_loader import (
     _RemoteDatasetLoader,
 )
-from pyrit.models import SeedDataset, SeedPrompt
+from pyrit.models import Modality, SeedDataset, SeedPrompt
 
 logger = logging.getLogger(__name__)
 
@@ -28,6 +28,11 @@ class _CBTBenchDataset(_RemoteDatasetLoader):
         - [@zhang2024cbtbench]
     """
 
+    # Metadata
+    modalities: tuple[Modality, ...] = (Modality.TEXT,)
+    size: str = "small"  # 20 core_fine_seed therapy seeds (default config)
+    tags: frozenset[str] = frozenset({"safety", "medical"})
+
     def __init__(
         self,
         *,
diff --git a/pyrit/datasets/seed_datasets/remote/ccp_sensitive_prompts_dataset.py b/pyrit/datasets/seed_datasets/remote/ccp_sensitive_prompts_dataset.py
index 752a1f4c6..e73b187a6 100644
--- a/pyrit/datasets/seed_datasets/remote/ccp_sensitive_prompts_dataset.py
+++ b/pyrit/datasets/seed_datasets/remote/ccp_sensitive_prompts_dataset.py
@@ -6,7 +6,7 @@
 from pyrit.datasets.seed_datasets.remote.remote_dataset_loader import (
     _RemoteDatasetLoader,
 )
-from pyrit.models import SeedDataset, SeedPrompt
+from pyrit.models import Modality, SeedDataset, SeedPrompt
 
 logger = logging.getLogger(__name__)
 
@@ -21,6 +21,11 @@ class _CCPSensitivePromptsDataset(_RemoteDatasetLoader):
     Reference: [@promptfoo2025ccp]
     """
 
+    # Metadata
+    modalities: tuple[Modality, ...] = (Modality.TEXT,)
+    size: str = "large"  # 1360 censorship-sensitive prompts (single-language Mandarin)
+    tags: frozenset[str] = frozenset({"safety", "multilingual"})
+
     def __init__(
         self,
         *,
diff --git a/pyrit/datasets/seed_datasets/remote/comic_jailbreak_dataset.py b/pyrit/datasets/seed_datasets/remote/comic_jailbreak_dataset.py
index b4d43bca0..0ec8c216e 100644
--- a/pyrit/datasets/seed_datasets/remote/comic_jailbreak_dataset.py
+++ b/pyrit/datasets/seed_datasets/remote/comic_jailbreak_dataset.py
@@ -12,7 +12,7 @@
 from pyrit.datasets.seed_datasets.remote.remote_dataset_loader import (
     _RemoteDatasetLoader,
 )
-from pyrit.models import Seed, SeedDataset, SeedObjective, SeedPrompt
+from pyrit.models import Modality, Seed, SeedDataset, SeedObjective, SeedPrompt
 
 logger = logging.getLogger(__name__)
 
@@ -92,8 +92,8 @@ class _ComicJailbreakDataset(_RemoteDatasetLoader):
         "sexual",
         "privacy",
     )
-    modalities: tuple[str, ...] = ("text", "image")
-    size: str = "large"  # 300 goals × 5 templates
+    modalities: tuple[Modality, ...] = (Modality.TEXT, Modality.IMAGE)
+    size: str = "large"  # 3501 image-text jailbreak prompts
     tags: frozenset[str] = frozenset({"safety", "multimodal"})
 
     def __init__(
diff --git a/pyrit/datasets/seed_datasets/remote/darkbench_dataset.py b/pyrit/datasets/seed_datasets/remote/darkbench_dataset.py
index 97c5bbf5d..93393242f 100644
--- a/pyrit/datasets/seed_datasets/remote/darkbench_dataset.py
+++ b/pyrit/datasets/seed_datasets/remote/darkbench_dataset.py
@@ -4,7 +4,7 @@
 from pyrit.datasets.seed_datasets.remote.remote_dataset_loader import (
     _RemoteDatasetLoader,
 )
-from pyrit.models import SeedDataset, SeedPrompt
+from pyrit.models import Modality, SeedDataset, SeedPrompt
 
 
 class _DarkBenchDataset(_RemoteDatasetLoader):
@@ -23,6 +23,11 @@ class _DarkBenchDataset(_RemoteDatasetLoader):
         - https://openreview.net/forum?id=odjMSBSWRt
     """
 
+    # Metadata
+    modalities: tuple[Modality, ...] = (Modality.TEXT,)
+    size: str = "large"  # 660 prompts across 6 dark-pattern categories
+    tags: frozenset[str] = frozenset({"default", "safety"})
+
     def __init__(
         self,
         *,
diff --git a/pyrit/datasets/seed_datasets/remote/equitymedqa_dataset.py b/pyrit/datasets/seed_datasets/remote/equitymedqa_dataset.py
index 1c3377286..647d1b9eb 100644
--- a/pyrit/datasets/seed_datasets/remote/equitymedqa_dataset.py
+++ b/pyrit/datasets/seed_datasets/remote/equitymedqa_dataset.py
@@ -8,7 +8,7 @@
 from pyrit.datasets.seed_datasets.remote.remote_dataset_loader import (
     _RemoteDatasetLoader,
 )
-from pyrit.models import SeedDataset, SeedPrompt
+from pyrit.models import Modality, SeedDataset, SeedPrompt
 
 logger = logging.getLogger(__name__)
 
@@ -24,6 +24,11 @@ class _EquityMedQADataset(_RemoteDatasetLoader):
     Reference: [@pfohl2024equitymedqa]
     """
 
+    # Metadata
+    modalities: tuple[Modality, ...] = (Modality.TEXT,)
+    size: str = "huge"  # 5565 prompts across 11 medical-bias subsets
+    tags: frozenset[str] = frozenset({"safety", "bias", "medical"})
+
     DATA_SUBSETS: list[str] = [
         "cc_llm",
         "cc_manual",
diff --git a/pyrit/datasets/seed_datasets/remote/forbidden_questions_dataset.py b/pyrit/datasets/seed_datasets/remote/forbidden_questions_dataset.py
index d884293eb..6ac387051 100644
--- a/pyrit/datasets/seed_datasets/remote/forbidden_questions_dataset.py
+++ b/pyrit/datasets/seed_datasets/remote/forbidden_questions_dataset.py
@@ -6,7 +6,7 @@
 from pyrit.datasets.seed_datasets.remote.remote_dataset_loader import (
     _RemoteDatasetLoader,
 )
-from pyrit.models import SeedDataset, SeedPrompt
+from pyrit.models import Modality, SeedDataset, SeedPrompt
 
 logger = logging.getLogger(__name__)
 
@@ -25,6 +25,11 @@ class _ForbiddenQuestionsDataset(_RemoteDatasetLoader):
     Website: https://jailbreak-llms.xinyueshen.me/
     """
 
+    # Metadata
+    modalities: tuple[Modality, ...] = (Modality.TEXT,)
+    size: str = "medium"  # 390 questions (13 scenarios x 30 questions)
+    tags: frozenset[str] = frozenset({"default", "safety", "jailbreak"})
+
     def __init__(
         self,
         *,
diff --git a/pyrit/datasets/seed_datasets/remote/harmbench_dataset.py b/pyrit/datasets/seed_datasets/remote/harmbench_dataset.py
index 4afcdb2c1..ca05447df 100644
--- a/pyrit/datasets/seed_datasets/remote/harmbench_dataset.py
+++ b/pyrit/datasets/seed_datasets/remote/harmbench_dataset.py
@@ -6,7 +6,7 @@
 from pyrit.datasets.seed_datasets.remote.remote_dataset_loader import (
     _RemoteDatasetLoader,
 )
-from pyrit.models import SeedDataset, SeedObjective
+from pyrit.models import Modality, SeedDataset, SeedObjective
 
 
 class _HarmBenchDataset(_RemoteDatasetLoader):
@@ -21,8 +21,8 @@ class _HarmBenchDataset(_RemoteDatasetLoader):
 
     # Metadata
     harm_categories: list[str] = ["cybercrime", "illegal", "harmful", "chemical_biological", "harassment"]
-    modalities: list[str] = ["text"]
-    size: str = "large"  # 504 seeds
+    modalities: tuple[Modality, ...] = (Modality.TEXT,)
+    size: str = "medium"  # 400 harmful behaviors
     tags: set[str] = {"default", "safety"}
 
     def __init__(
diff --git a/pyrit/datasets/seed_datasets/remote/harmbench_multimodal_dataset.py b/pyrit/datasets/seed_datasets/remote/harmbench_multimodal_dataset.py
index 514c5a1cb..d77767d93 100644
--- a/pyrit/datasets/seed_datasets/remote/harmbench_multimodal_dataset.py
+++ b/pyrit/datasets/seed_datasets/remote/harmbench_multimodal_dataset.py
@@ -12,7 +12,7 @@
 from pyrit.datasets.seed_datasets.remote.remote_dataset_loader import (
     _RemoteDatasetLoader,
 )
-from pyrit.models import SeedDataset, SeedPrompt
+from pyrit.models import Modality, SeedDataset, SeedPrompt
 
 logger = logging.getLogger(__name__)
 
@@ -43,6 +43,11 @@ class _HarmBenchMultimodalDataset(_RemoteDatasetLoader):
     Paper: [@mazeika2024harmbench]
     """
 
+    # Metadata
+    modalities: tuple[Modality, ...] = (Modality.TEXT, Modality.IMAGE)
+    size: str = "medium"  # 220 harmful multimodal behaviors
+    tags: frozenset[str] = frozenset({"safety", "jailbreak", "multimodal"})
+
     def __init__(
         self,
         *,
diff --git a/pyrit/datasets/seed_datasets/remote/harmful_qa_dataset.py b/pyrit/datasets/seed_datasets/remote/harmful_qa_dataset.py
index a2a8451a9..9d0a806e6 100644
--- a/pyrit/datasets/seed_datasets/remote/harmful_qa_dataset.py
+++ b/pyrit/datasets/seed_datasets/remote/harmful_qa_dataset.py
@@ -6,7 +6,7 @@
 from pyrit.datasets.seed_datasets.remote.remote_dataset_loader import (
     _RemoteDatasetLoader,
 )
-from pyrit.models import SeedDataset, SeedPrompt
+from pyrit.models import Modality, SeedDataset, SeedPrompt
 
 logger = logging.getLogger(__name__)
 
@@ -28,6 +28,11 @@ class _HarmfulQADataset(_RemoteDatasetLoader):
 
     HF_DATASET_NAME: str = "declare-lab/HarmfulQA"
 
+    # Metadata
+    modalities: tuple[Modality, ...] = (Modality.TEXT,)
+    size: str = "large"  # 1960 harmful questions by academic topic
+    tags: frozenset[str] = frozenset({"default", "safety", "jailbreak"})
+
     def __init__(
         self,
         *,
diff --git a/pyrit/datasets/seed_datasets/remote/jbb_behaviors_dataset.py b/pyrit/datasets/seed_datasets/remote/jbb_behaviors_dataset.py
index e638b5144..8c1ac3de8 100644
--- a/pyrit/datasets/seed_datasets/remote/jbb_behaviors_dataset.py
+++ b/pyrit/datasets/seed_datasets/remote/jbb_behaviors_dataset.py
@@ -6,7 +6,7 @@
 from pyrit.datasets.seed_datasets.remote.remote_dataset_loader import (
     _RemoteDatasetLoader,
 )
-from pyrit.models import SeedDataset, SeedPrompt
+from pyrit.models import Modality, SeedDataset, SeedPrompt
 
 logger = logging.getLogger(__name__)
 
@@ -24,6 +24,11 @@ class _JBBBehaviorsDataset(_RemoteDatasetLoader):
     before using these prompts against production LLMs.
     """
 
+    # Metadata
+    modalities: tuple[Modality, ...] = (Modality.TEXT,)
+    size: str = "small"  # 100 harmful behaviors across 10 categories
+    tags: frozenset[str] = frozenset({"safety", "jailbreak"})
+
     def __init__(
         self,
         *,
diff --git a/pyrit/datasets/seed_datasets/remote/librai_do_not_answer_dataset.py b/pyrit/datasets/seed_datasets/remote/librai_do_not_answer_dataset.py
index 9f007aa34..7029753b6 100644
--- a/pyrit/datasets/seed_datasets/remote/librai_do_not_answer_dataset.py
+++ b/pyrit/datasets/seed_datasets/remote/librai_do_not_answer_dataset.py
@@ -6,7 +6,7 @@
 from pyrit.datasets.seed_datasets.remote.remote_dataset_loader import (
     _RemoteDatasetLoader,
 )
-from pyrit.models import SeedDataset, SeedPrompt
+from pyrit.models import Modality, SeedDataset, SeedPrompt
 
 logger = logging.getLogger(__name__)
 
@@ -22,6 +22,11 @@ class _LibrAIDoNotAnswerDataset(_RemoteDatasetLoader):
     GitHub: https://github.com/libr-ai/do-not-answer
     """
 
+    # Metadata
+    modalities: tuple[Modality, ...] = (Modality.TEXT,)
+    size: str = "large"  # 939 prompts across multiple risk areas
+    tags: frozenset[str] = frozenset({"default", "safety", "refusal"})
+
     def __init__(
         self,
         *,
diff --git a/pyrit/datasets/seed_datasets/remote/llm_latent_adversarial_training_dataset.py b/pyrit/datasets/seed_datasets/remote/llm_latent_adversarial_training_dataset.py
index f881fe0cb..77fb22db4 100644
--- a/pyrit/datasets/seed_datasets/remote/llm_latent_adversarial_training_dataset.py
+++ b/pyrit/datasets/seed_datasets/remote/llm_latent_adversarial_training_dataset.py
@@ -6,7 +6,7 @@
 from pyrit.datasets.seed_datasets.remote.remote_dataset_loader import (
     _RemoteDatasetLoader,
 )
-from pyrit.models import SeedDataset, SeedPrompt
+from pyrit.models import Modality, SeedDataset, SeedPrompt
 
 logger = logging.getLogger(__name__)
 
@@ -21,6 +21,11 @@ class _LLMLatentAdversarialTrainingDataset(_RemoteDatasetLoader):
     Reference: [@sheshadri2024lat]
     """
 
+    # Metadata
+    modalities: tuple[Modality, ...] = (Modality.TEXT,)
+    size: str = "large"  # 4948 harmful prompts
+    tags: frozenset[str] = frozenset({"default", "safety", "jailbreak"})
+
     def __init__(
         self,
         *,
diff --git a/pyrit/datasets/seed_datasets/remote/medsafetybench_dataset.py b/pyrit/datasets/seed_datasets/remote/medsafetybench_dataset.py
index ab2390723..e99f11d83 100644
--- a/pyrit/datasets/seed_datasets/remote/medsafetybench_dataset.py
+++ b/pyrit/datasets/seed_datasets/remote/medsafetybench_dataset.py
@@ -7,7 +7,7 @@
 from pyrit.datasets.seed_datasets.remote.remote_dataset_loader import (
     _RemoteDatasetLoader,
 )
-from pyrit.models import SeedDataset, SeedPrompt
+from pyrit.models import Modality, SeedDataset, SeedPrompt
 
 logger = logging.getLogger(__name__)
 
@@ -23,6 +23,11 @@ class _MedSafetyBenchDataset(_RemoteDatasetLoader):
     Paper: [@han2024medsafetybench]
     """
 
+    # Metadata
+    modalities: tuple[Modality, ...] = (Modality.TEXT,)
+    size: str = "huge"  # 76174 medical-safety prompts (combined train+test+generated)
+    tags: frozenset[str] = frozenset({"safety", "medical"})
+
     def __init__(
         self,
         *,
diff --git a/pyrit/datasets/seed_datasets/remote/mlcommons_ailuminate_dataset.py b/pyrit/datasets/seed_datasets/remote/mlcommons_ailuminate_dataset.py
index f954bc994..32698ca1a 100644
--- a/pyrit/datasets/seed_datasets/remote/mlcommons_ailuminate_dataset.py
+++ b/pyrit/datasets/seed_datasets/remote/mlcommons_ailuminate_dataset.py
@@ -7,7 +7,7 @@
 from pyrit.datasets.seed_datasets.remote.remote_dataset_loader import (
     _RemoteDatasetLoader,
 )
-from pyrit.models import SeedDataset, SeedPrompt
+from pyrit.models import Modality, SeedDataset, SeedPrompt
 
 logger = logging.getLogger(__name__)
 
@@ -23,6 +23,11 @@ class _MLCommonsAILuminateDataset(_RemoteDatasetLoader):
     Paper: [@vidgen2024ailuminate]
     """
 
+    # Metadata
+    modalities: tuple[Modality, ...] = (Modality.TEXT,)
+    size: str = "large"  # 1,200 hazard-category prompts
+    tags: frozenset[str] = frozenset({"default", "safety"})
+
     HAZARD_CATEGORIES_MAP = {
         "vcr": "Violent Crimes",
         "src": "Sex-Related Crimes",
diff --git a/pyrit/datasets/seed_datasets/remote/multilingual_vulnerability_dataset.py b/pyrit/datasets/seed_datasets/remote/multilingual_vulnerability_dataset.py
index 4f4db77cd..5c94eb1bf 100644
--- a/pyrit/datasets/seed_datasets/remote/multilingual_vulnerability_dataset.py
+++ b/pyrit/datasets/seed_datasets/remote/multilingual_vulnerability_dataset.py
@@ -6,7 +6,7 @@
 from pyrit.datasets.seed_datasets.remote.remote_dataset_loader import (
     _RemoteDatasetLoader,
 )
-from pyrit.models import SeedDataset, SeedPrompt
+from pyrit.models import Modality, SeedDataset, SeedPrompt
 
 logger = logging.getLogger(__name__)
 
@@ -22,6 +22,11 @@ class _MultilingualVulnerabilityDataset(_RemoteDatasetLoader):
     GitHub: https://github.com/CarsonDon/Multilingual-Vuln-LLMs
     """
 
+    # Metadata
+    modalities: tuple[Modality, ...] = (Modality.TEXT,)
+    size: str = "small"  # 70 multilingual vulnerability prompts
+    tags: frozenset[str] = frozenset({"default", "safety", "multilingual"})
+
     def __init__(
         self,
         *,
diff --git a/pyrit/datasets/seed_datasets/remote/or_bench_dataset.py b/pyrit/datasets/seed_datasets/remote/or_bench_dataset.py
index b4aa647d4..4bd3ae674 100644
--- a/pyrit/datasets/seed_datasets/remote/or_bench_dataset.py
+++ b/pyrit/datasets/seed_datasets/remote/or_bench_dataset.py
@@ -6,7 +6,7 @@
 from pyrit.datasets.seed_datasets.remote.remote_dataset_loader import (
     _RemoteDatasetLoader,
 )
-from pyrit.models import SeedDataset, SeedPrompt
+from pyrit.models import Modality, SeedDataset, SeedPrompt
 
 logger = logging.getLogger(__name__)
 
@@ -30,6 +30,12 @@ class _ORBenchBaseDataset(_RemoteDatasetLoader):
     CONFIG: str
     DESCRIPTION: str
 
+    should_register = False  # abstract base — subclasses register themselves
+
+    # Metadata shared across all OR-Bench subclasses; subclasses override `size`.
+    modalities: tuple[Modality, ...] = (Modality.TEXT,)
+    tags: frozenset[str] = frozenset({"default", "safety", "refusal"})
+
     def __init__(self, *, split: str = "train") -> None:
         """
         Initialize the OR-Bench dataset loader.
@@ -99,6 +105,8 @@ class _ORBench80KDataset(_ORBenchBaseDataset):
         "OR-Bench 80K contains ~80k over-refusal prompts categorized into 10 rejection "
         "categories. This is the main comprehensive benchmark for evaluating LLM over-refusal."
     )
+    size: str = "huge"  # 80359 over-refusal prompts
+    should_register = True
 
     @property
     def dataset_name(self) -> str:
@@ -119,6 +127,8 @@ class _ORBenchHardDataset(_ORBenchBaseDataset):
         "OR-Bench Hard-1K contains ~1k challenging safe prompts that commonly trigger "
         "over-refusal in language models. These prompts should be answerable without refusing."
     )
+    size: str = "large"  # 1319 challenging safe prompts
+    should_register = True
 
     @property
     def dataset_name(self) -> str:
@@ -140,6 +150,8 @@ class _ORBenchToxicDataset(_ORBenchBaseDataset):
         "OR-Bench Toxic contains toxic prompts that language models should correctly refuse. "
         "Used as a contrast set to evaluate refusal calibration."
     )
+    size: str = "large"  # 655 toxic prompts for refusal calibration
+    should_register = True
 
     @property
     def dataset_name(self) -> str:
diff --git a/pyrit/datasets/seed_datasets/remote/pku_safe_rlhf_dataset.py b/pyrit/datasets/seed_datasets/remote/pku_safe_rlhf_dataset.py
index 2921bb032..4733cf1af 100644
--- a/pyrit/datasets/seed_datasets/remote/pku_safe_rlhf_dataset.py
+++ b/pyrit/datasets/seed_datasets/remote/pku_safe_rlhf_dataset.py
@@ -7,7 +7,7 @@
 from pyrit.datasets.seed_datasets.remote.remote_dataset_loader import (
     _RemoteDatasetLoader,
 )
-from pyrit.models import SeedDataset, SeedPrompt
+from pyrit.models import Modality, SeedDataset, SeedPrompt
 
 logger = logging.getLogger(__name__)
 
@@ -23,6 +23,11 @@ class _PKUSafeRLHFDataset(_RemoteDatasetLoader):
     Paper: [@ji2024pkusaferlhf]
     """
 
+    # Metadata
+    modalities: tuple[Modality, ...] = (Modality.TEXT,)
+    size: str = "huge"  # 73907 prompt-response pairs across 19 harm categories
+    tags: frozenset[str] = frozenset({"default", "safety"})
+
     def __init__(
         self,
         *,
diff --git a/pyrit/datasets/seed_datasets/remote/promptintel_dataset.py b/pyrit/datasets/seed_datasets/remote/promptintel_dataset.py
index 7af64c4fe..b2b1845c4 100644
--- a/pyrit/datasets/seed_datasets/remote/promptintel_dataset.py
+++ b/pyrit/datasets/seed_datasets/remote/promptintel_dataset.py
@@ -12,7 +12,7 @@
 from pyrit.datasets.seed_datasets.remote.remote_dataset_loader import (
     _RemoteDatasetLoader,
 )
-from pyrit.models import SeedDataset, SeedPrompt
+from pyrit.models import Modality, SeedDataset, SeedPrompt
 
 logger = logging.getLogger(__name__)
 
@@ -64,6 +64,11 @@ class _PromptIntelDataset(_RemoteDatasetLoader):
     Use responsibly and consult your legal department before using for testing.
     """
 
+    # Metadata
+    modalities: tuple[Modality, ...] = (Modality.TEXT,)
+    size: str = "medium"  # indicator count varies with registry contents; gated by API key
+    tags: frozenset[str] = frozenset({"safety", "jailbreak", "cybersecurity"})
+
     API_BASE_URL = "https://api.promptintel.novahunting.ai/api/v1"
     PROMPT_WEB_URL = "https://promptintel.novahunting.ai/prompt"
     MAX_PAGE_LIMIT = 100
diff --git a/pyrit/datasets/seed_datasets/remote/red_team_social_bias_dataset.py b/pyrit/datasets/seed_datasets/remote/red_team_social_bias_dataset.py
index 75b4fe139..12b4072b7 100644
--- a/pyrit/datasets/seed_datasets/remote/red_team_social_bias_dataset.py
+++ b/pyrit/datasets/seed_datasets/remote/red_team_social_bias_dataset.py
@@ -8,7 +8,7 @@
 from pyrit.datasets.seed_datasets.remote.remote_dataset_loader import (
     _RemoteDatasetLoader,
 )
-from pyrit.models import SeedDataset, SeedPrompt
+from pyrit.models import Modality, SeedDataset, SeedPrompt
 
 logger = logging.getLogger(__name__)
 
@@ -24,6 +24,11 @@ class _RedTeamSocialBiasDataset(_RemoteDatasetLoader):
     Reference: [@vantaylor2024socialbias]
     """
 
+    # Metadata
+    modalities: tuple[Modality, ...] = (Modality.TEXT,)
+    size: str = "huge"  # 40750 social-bias prompts (multi-turn expansion of source rows)
+    tags: frozenset[str] = frozenset({"safety", "bias", "multiturn"})
+
     def __init__(
         self,
         *,
diff --git a/pyrit/datasets/seed_datasets/remote/salad_bench_dataset.py b/pyrit/datasets/seed_datasets/remote/salad_bench_dataset.py
index 413dbd915..9a179ee64 100644
--- a/pyrit/datasets/seed_datasets/remote/salad_bench_dataset.py
+++ b/pyrit/datasets/seed_datasets/remote/salad_bench_dataset.py
@@ -7,7 +7,7 @@
 from pyrit.datasets.seed_datasets.remote.remote_dataset_loader import (
     _RemoteDatasetLoader,
 )
-from pyrit.models import SeedDataset, SeedPrompt
+from pyrit.models import Modality, SeedDataset, SeedPrompt
 
 logger = logging.getLogger(__name__)
 
@@ -32,6 +32,11 @@ class _SaladBenchDataset(_RemoteDatasetLoader):
 
     HF_DATASET_NAME: str = "walledai/SaladBench"
 
+    # Metadata
+    modalities: tuple[Modality, ...] = (Modality.TEXT,)
+    size: str = "huge"  # 21318 harmful questions across 6 domains, 16 tasks, 65+ categories
+    tags: frozenset[str] = frozenset({"default", "safety", "jailbreak"})
+
     def __init__(
         self,
         *,
diff --git a/pyrit/datasets/seed_datasets/remote/sgxstest_dataset.py b/pyrit/datasets/seed_datasets/remote/sgxstest_dataset.py
index eb6a8520f..0871f7161 100644
--- a/pyrit/datasets/seed_datasets/remote/sgxstest_dataset.py
+++ b/pyrit/datasets/seed_datasets/remote/sgxstest_dataset.py
@@ -8,7 +8,7 @@
 from pyrit.datasets.seed_datasets.remote.remote_dataset_loader import (
     _RemoteDatasetLoader,
 )
-from pyrit.models import SeedDataset, SeedObjective
+from pyrit.models import Modality, SeedDataset, SeedObjective
 
 logger = logging.getLogger(__name__)
 
@@ -66,9 +66,9 @@ class _SGXSTestDataset(_RemoteDatasetLoader):
         "safe contexts",
         "safe targets",
     ]
-    modalities: list[str] = ["text"]
-    size: str = "medium"  # 200 prompts
-    tags: set[str] = {"default", "safety", "multilingual_culture"}
+    modalities: tuple[Modality, ...] = (Modality.TEXT,)
+    size: str = "small"  # 100 prompts
+    tags: set[str] = {"safety", "multilingual"}
 
     def __init__(
         self,
diff --git a/pyrit/datasets/seed_datasets/remote/simple_safety_tests_dataset.py b/pyrit/datasets/seed_datasets/remote/simple_safety_tests_dataset.py
index d92007c52..71e05b41c 100644
--- a/pyrit/datasets/seed_datasets/remote/simple_safety_tests_dataset.py
+++ b/pyrit/datasets/seed_datasets/remote/simple_safety_tests_dataset.py
@@ -6,7 +6,7 @@
 from pyrit.datasets.seed_datasets.remote.remote_dataset_loader import (
     _RemoteDatasetLoader,
 )
-from pyrit.models import SeedDataset, SeedPrompt
+from pyrit.models import Modality, SeedDataset, SeedPrompt
 
 logger = logging.getLogger(__name__)
 
@@ -28,6 +28,11 @@ class _SimpleSafetyTestsDataset(_RemoteDatasetLoader):
 
     HF_DATASET_NAME: str = "Bertievidgen/SimpleSafetyTests"
 
+    # Metadata
+    modalities: tuple[Modality, ...] = (Modality.TEXT,)
+    size: str = "small"  # 100 critical safety test prompts
+    tags: frozenset[str] = frozenset({"safety"})
+
     def __init__(
         self,
         *,
diff --git a/pyrit/datasets/seed_datasets/remote/sorry_bench_dataset.py b/pyrit/datasets/seed_datasets/remote/sorry_bench_dataset.py
index 407fc8810..735e8baf2 100644
--- a/pyrit/datasets/seed_datasets/remote/sorry_bench_dataset.py
+++ b/pyrit/datasets/seed_datasets/remote/sorry_bench_dataset.py
@@ -8,7 +8,7 @@
 from pyrit.datasets.seed_datasets.remote.remote_dataset_loader import (
     _RemoteDatasetLoader,
 )
-from pyrit.models import SeedDataset, SeedPrompt
+from pyrit.models import Modality, SeedDataset, SeedPrompt
 
 logger = logging.getLogger(__name__)
 
@@ -23,6 +23,11 @@ class _SorryBenchDataset(_RemoteDatasetLoader):
     Reference: [@xie2024sorrybench]
     """
 
+    # Metadata
+    modalities: tuple[Modality, ...] = (Modality.TEXT,)
+    size: str = "medium"  # 440 base prompts (style mutations not loaded by default)
+    tags: frozenset[str] = frozenset({"safety", "jailbreak", "synthetic"})
+
     VALID_CATEGORIES = [
         "Personal Insulting Words",
         "Social-group Insulting Words",
diff --git a/pyrit/datasets/seed_datasets/remote/sosbench_dataset.py b/pyrit/datasets/seed_datasets/remote/sosbench_dataset.py
index 61b215c4f..d2f908849 100644
--- a/pyrit/datasets/seed_datasets/remote/sosbench_dataset.py
+++ b/pyrit/datasets/seed_datasets/remote/sosbench_dataset.py
@@ -6,7 +6,7 @@
 from pyrit.datasets.seed_datasets.remote.remote_dataset_loader import (
     _RemoteDatasetLoader,
 )
-from pyrit.models import SeedDataset, SeedPrompt
+from pyrit.models import Modality, SeedDataset, SeedPrompt
 
 logger = logging.getLogger(__name__)
 
@@ -22,6 +22,11 @@ class _SOSBenchDataset(_RemoteDatasetLoader):
     Reference: [@jiang2025sosbench]
     """
 
+    # Metadata
+    modalities: tuple[Modality, ...] = (Modality.TEXT,)
+    size: str = "large"  # 3,000 hazard-focused scientific prompts across 6 domains
+    tags: frozenset[str] = frozenset({"safety", "medical", "cybersecurity"})
+
     def __init__(
         self,
         *,
diff --git a/pyrit/datasets/seed_datasets/remote/tdc23_redteaming_dataset.py b/pyrit/datasets/seed_datasets/remote/tdc23_redteaming_dataset.py
index 104be4d10..07561aff9 100644
--- a/pyrit/datasets/seed_datasets/remote/tdc23_redteaming_dataset.py
+++ b/pyrit/datasets/seed_datasets/remote/tdc23_redteaming_dataset.py
@@ -6,7 +6,7 @@
 from pyrit.datasets.seed_datasets.remote.remote_dataset_loader import (
     _RemoteDatasetLoader,
 )
-from pyrit.models import SeedDataset, SeedPrompt
+from pyrit.models import Modality, SeedDataset, SeedPrompt
 
 logger = logging.getLogger(__name__)
 
@@ -22,6 +22,11 @@ class _TDC23RedteamingDataset(_RemoteDatasetLoader):
     Reference: [@mazeika2023tdc]
     """
 
+    # Metadata
+    modalities: tuple[Modality, ...] = (Modality.TEXT,)
+    size: str = "small"  # 100 narrative-style harmful prompts
+    tags: frozenset[str] = frozenset({"safety", "jailbreak"})
+
     def __init__(
         self,
         *,
diff --git a/pyrit/datasets/seed_datasets/remote/toxic_chat_dataset.py b/pyrit/datasets/seed_datasets/remote/toxic_chat_dataset.py
index fcfa68297..61e6a4ac9 100644
--- a/pyrit/datasets/seed_datasets/remote/toxic_chat_dataset.py
+++ b/pyrit/datasets/seed_datasets/remote/toxic_chat_dataset.py
@@ -8,7 +8,7 @@
 from pyrit.datasets.seed_datasets.remote.remote_dataset_loader import (
     _RemoteDatasetLoader,
 )
-from pyrit.models import SeedDataset, SeedPrompt
+from pyrit.models import Modality, SeedDataset, SeedPrompt
 
 logger = logging.getLogger(__name__)
 
@@ -32,6 +32,11 @@ class _ToxicChatDataset(_RemoteDatasetLoader):
 
     HF_DATASET_NAME: str = "lmsys/toxic-chat"
 
+    # Metadata
+    modalities: tuple[Modality, ...] = (Modality.TEXT,)
+    size: str = "huge"  # 5082 real user-chatbot conversations from Chatbot Arena
+    tags: frozenset[str] = frozenset({"default", "safety", "multiturn"})
+
     OPENAI_MODERATION_THRESHOLD: float = 0.8
 
     def __init__(
diff --git a/pyrit/datasets/seed_datasets/remote/transphobia_awareness_dataset.py b/pyrit/datasets/seed_datasets/remote/transphobia_awareness_dataset.py
index 73b8a8e5e..c64c1172d 100644
--- a/pyrit/datasets/seed_datasets/remote/transphobia_awareness_dataset.py
+++ b/pyrit/datasets/seed_datasets/remote/transphobia_awareness_dataset.py
@@ -9,7 +9,7 @@
 from pyrit.datasets.seed_datasets.remote.remote_dataset_loader import (
     _RemoteDatasetLoader,
 )
-from pyrit.models import SeedDataset, SeedPrompt
+from pyrit.models import Modality, SeedDataset, SeedPrompt
 
 logger = logging.getLogger(__name__)
 
@@ -34,6 +34,11 @@ class _TransphobiaAwarenessDataset(_RemoteDatasetLoader):
     ACM Transactions on Computer-Human Interaction (2018).
     """
 
+    # Metadata
+    modalities: tuple[Modality, ...] = (Modality.TEXT,)
+    size: str = "medium"  # 300 Quora questions on transgender / non-binary topics
+    tags: frozenset[str] = frozenset({"default", "safety", "bias"})
+
     RATINGS_URL = "https://zenodo.org/records/15482694/files/Ratings.xlsx?download=1"
     QUESTION_RESPONSE_PAIRS_URL = "https://zenodo.org/records/15482694/files/Question_Response_Pairs.xlsx?download=1"
     QUORA_QUESTION_LIST_URL = "https://zenodo.org/records/15482694/files/Quora%20Question%20List.xlsx?download=1"
diff --git a/pyrit/datasets/seed_datasets/remote/visual_leak_bench_dataset.py b/pyrit/datasets/seed_datasets/remote/visual_leak_bench_dataset.py
index 2edd921eb..09f47de4c 100644
--- a/pyrit/datasets/seed_datasets/remote/visual_leak_bench_dataset.py
+++ b/pyrit/datasets/seed_datasets/remote/visual_leak_bench_dataset.py
@@ -12,7 +12,7 @@
 from pyrit.datasets.seed_datasets.remote.remote_dataset_loader import (
     _RemoteDatasetLoader,
 )
-from pyrit.models import SeedDataset, SeedPrompt
+from pyrit.models import Modality, SeedDataset, SeedPrompt
 
 logger = logging.getLogger(__name__)
 
@@ -73,8 +73,8 @@ class _VisualLeakBenchDataset(_RemoteDatasetLoader):
     )
 
     tags: frozenset[str] = frozenset({"default", "safety", "privacy"})
-    size: str = "large"
-    modalities: tuple[str, ...] = ("image", "text")
+    size: str = "large"  # 2000 image-text PII / OCR-injection prompts
+    modalities: tuple[Modality, ...] = (Modality.IMAGE, Modality.TEXT)
     harm_categories: tuple[str, ...] = ("privacy", "pii_leakage", "ocr_injection")
 
     def __init__(
diff --git a/pyrit/datasets/seed_datasets/remote/vlguard_dataset.py b/pyrit/datasets/seed_datasets/remote/vlguard_dataset.py
index 1ab86cfe7..c9e8e1356 100644
--- a/pyrit/datasets/seed_datasets/remote/vlguard_dataset.py
+++ b/pyrit/datasets/seed_datasets/remote/vlguard_dataset.py
@@ -15,7 +15,7 @@
 from pyrit.datasets.seed_datasets.remote.remote_dataset_loader import (
     _RemoteDatasetLoader,
 )
-from pyrit.models import SeedDataset, SeedPrompt
+from pyrit.models import Modality, SeedDataset, SeedPrompt
 
 logger = logging.getLogger(__name__)
 
@@ -93,6 +93,11 @@ class _VLGuardDataset(_RemoteDatasetLoader):
     Paper: Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models (ICML 2024)
     """
 
+    # Metadata
+    modalities: tuple[Modality, ...] = (Modality.TEXT, Modality.IMAGE)
+    size: str = "large"  # 884 image-instruction pairs across 4 categories
+    tags: frozenset[str] = frozenset({"safety", "multimodal"})
+
     def __init__(
         self,
         *,
diff --git a/pyrit/datasets/seed_datasets/remote/vlsu_multimodal_dataset.py b/pyrit/datasets/seed_datasets/remote/vlsu_multimodal_dataset.py
index 74ccf9434..26a2460af 100644
--- a/pyrit/datasets/seed_datasets/remote/vlsu_multimodal_dataset.py
+++ b/pyrit/datasets/seed_datasets/remote/vlsu_multimodal_dataset.py
@@ -12,7 +12,7 @@
 from pyrit.datasets.seed_datasets.remote.remote_dataset_loader import (
     _RemoteDatasetLoader,
 )
-from pyrit.models import SeedDataset, SeedPrompt
+from pyrit.models import Modality, SeedDataset, SeedPrompt
 
 logger = logging.getLogger(__name__)
 
@@ -52,6 +52,11 @@ class _VLSUMultimodalDataset(_RemoteDatasetLoader):
     Reference: [@palaskar2025vlsu]
     """
 
+    # Metadata
+    modalities: tuple[Modality, ...] = (Modality.TEXT, Modality.IMAGE)
+    size: str = "huge"  # 11074 image-text safety annotations
+    tags: frozenset[str] = frozenset({"default", "safety", "multimodal"})
+
     def __init__(
         self,
         *,
diff --git a/pyrit/datasets/seed_datasets/remote/xstest_dataset.py b/pyrit/datasets/seed_datasets/remote/xstest_dataset.py
index ea50eecf1..3b84780f9 100644
--- a/pyrit/datasets/seed_datasets/remote/xstest_dataset.py
+++ b/pyrit/datasets/seed_datasets/remote/xstest_dataset.py
@@ -7,7 +7,7 @@
 from pyrit.datasets.seed_datasets.remote.remote_dataset_loader import (
     _RemoteDatasetLoader,
 )
-from pyrit.models import SeedDataset, SeedPrompt
+from pyrit.models import Modality, SeedDataset, SeedPrompt
 
 logger = logging.getLogger(__name__)
 
@@ -21,6 +21,11 @@ class _XSTestDataset(_RemoteDatasetLoader):
     Reference: https://github.com/paul-rottger/exaggerated-safety
     """
 
+    # Metadata
+    modalities: tuple[Modality, ...] = (Modality.TEXT,)
+    size: str = "medium"  # 450 safe + unsafe contrast prompts
+    tags: frozenset[str] = frozenset({"default", "safety", "refusal"})
+
     def __init__(
         self,
         *,
diff --git a/pyrit/datasets/seed_datasets/seed_metadata.py b/pyrit/datasets/seed_datasets/seed_metadata.py
index 33a4c8ead..8396a5189 100644
--- a/pyrit/datasets/seed_datasets/seed_metadata.py
+++ b/pyrit/datasets/seed_datasets/seed_metadata.py
@@ -26,6 +26,47 @@
 
 SeedDatasetSourceType = Literal["remote", "local"]
 
+# Canonical, *advisory* tag vocabulary for SeedDatasetMetadata.tags.
+#
+# Loaders may set custom tags, but contributors should reuse this vocabulary
+# whenever it fits to keep `SeedDatasetFilter` discovery consistent across
+# datasets. The metadata parser does NOT enforce this list — it is enforced as
+# a soft contract via tests/unit/datasets/test_seed_dataset_provider.py.
+#
+# Rule for the special "default" tag (applied when authoring/registering a
+# loader, not enforced at runtime): a dataset should be tagged "default" only
+# when ALL of the following hold:
+#
+#   1. Ungated  — no HuggingFace token, API key, auth, or signup required.
+#   2. Citable  — peer-reviewed paper or established benchmark, not a personal
+#                 collection or unpublished registry.
+#   3. Single-call — `await loader.fetch_dataset_async()` works with no
+#                    manual download or setup (auto-cached per-asset fetches
+#                    are fine).
+#   4. Size >= medium (>=100 prompts).
+#   5. Broadly applicable — not narrowly scoped to a vertical-specific domain
+#                           (e.g., medical, legal, cybersecurity). Cross-cutting
+#                           axes like `privacy`, `bias`, `multimodal`,
+#                           `multilingual`, `refusal`, and `jailbreak` DO count
+#                           as broadly applicable.
+RECOMMENDED_TAGS: frozenset[str] = frozenset(
+    {
+        "default",  # see rule above
+        "safety",  # universal for any harm/red-team content
+        "multimodal",  # image+text, audio+text, etc.
+        "multilingual",  # multiple natural languages
+        "privacy",  # privacy / PII content
+        "jailbreak",  # adversarial / jailbreak templates
+        "bias",  # fairness / bias-focused
+        "medical",  # medical / health domain
+        "legal",  # legal domain
+        "cybersecurity",  # cybersecurity / malware domain
+        "refusal",  # refusal-evaluation oriented (over-refusal, false-refusal, etc.)
+        "synthetic",  # programmatically generated content
+        "multiturn",  # multi-turn conversations
+    }
+)
+
 
 class SeedDatasetLoadTime(Enum):
     """Approximate time to load a dataset. Used to skip slow datasets in fast runs."""
diff --git a/pyrit/models/__init__.py b/pyrit/models/__init__.py
index 1093e1da0..0380dca23 100644
--- a/pyrit/models/__init__.py
+++ b/pyrit/models/__init__.py
@@ -24,7 +24,7 @@
 )
 from pyrit.models.embeddings import EmbeddingData, EmbeddingResponse, EmbeddingSupport, EmbeddingUsageInformation
 from pyrit.models.harm_definition import HarmDefinition, ScaleDescription, get_all_harm_definitions
-from pyrit.models.literals import ChatMessageRole, PromptDataType, PromptResponseError, SeedType
+from pyrit.models.literals import ChatMessageRole, Modality, PromptDataType, PromptResponseError, SeedType
 from pyrit.models.message import (
     Message,
     construct_response_from_request,
@@ -88,6 +88,7 @@
     "ImagePathDataTypeSerializer",
     "Message",
     "MessagePiece",
+    "Modality",
     "NextMessageSystemPromptPaths",
     "PromptDataType",
     "PromptResponseError",
diff --git a/pyrit/models/literals.py b/pyrit/models/literals.py
index 8c488eebe..a61b65a09 100644
--- a/pyrit/models/literals.py
+++ b/pyrit/models/literals.py
@@ -1,6 +1,7 @@
 # Copyright (c) Microsoft Corporation.
 # Licensed under the MIT license.
 
+from enum import Enum
 from typing import Literal
 
 PromptDataType = Literal[
@@ -29,3 +30,27 @@
 ChatMessageRole = Literal["system", "user", "assistant", "simulated_assistant", "tool", "developer"]
 
 SeedType = Literal["prompt", "objective", "simulated_conversation"]
+
+
+class Modality(str, Enum):
+    """
+    Canonical high-level modalities for dataset content and target capabilities.
+
+    Inherits from ``str`` so members compare equal to their string values
+    (e.g. ``Modality.TEXT == "text"``) and JSON-serialize as plain strings.
+    This keeps the enum interoperable with existing string-typed APIs while
+    giving authors autocomplete and lint-time typo protection.
+
+    Used by:
+      * ``SeedDatasetMetadata.modalities`` and dataset loader class attributes
+        to describe what content a dataset produces.
+
+    Not yet used by ``TargetCapabilities`` (which still uses ``PromptDataType``
+    with finer-grained ``image_path``/``audio_path``/``video_path`` storage
+    tokens). Unifying the two is tracked as a follow-up — see PR #1780.
+    """
+
+    TEXT = "text"
+    IMAGE = "image"
+    AUDIO = "audio"
+    VIDEO = "video"
diff --git a/tests/unit/datasets/test_seed_dataset_provider.py b/tests/unit/datasets/test_seed_dataset_provider.py
index 4eb058f6a..26ed16801 100644
--- a/tests/unit/datasets/test_seed_dataset_provider.py
+++ b/tests/unit/datasets/test_seed_dataset_provider.py
@@ -2,6 +2,7 @@
 # Licensed under the MIT license.
 
 import textwrap
+import typing
 import warnings
 from dataclasses import fields as dc_fields
 from pathlib import Path
@@ -10,16 +11,20 @@
 import pytest
 import yaml
 
+import pyrit.datasets.seed_datasets.remote  # noqa: F401  triggers loader registration
 from pyrit.datasets import SeedDatasetProvider
 from pyrit.datasets.seed_datasets.local.local_dataset_loader import _LocalDatasetLoader
 from pyrit.datasets.seed_datasets.remote.darkbench_dataset import _DarkBenchDataset
 from pyrit.datasets.seed_datasets.remote.harmbench_dataset import _HarmBenchDataset
+from pyrit.datasets.seed_datasets.remote.remote_dataset_loader import _RemoteDatasetLoader
 from pyrit.datasets.seed_datasets.seed_metadata import (
+    RECOMMENDED_TAGS,
     SeedDatasetFilter,
     SeedDatasetLoadTime,
     SeedDatasetMetadata,
+    SeedDatasetSizeCategory,
 )
-from pyrit.models import SeedDataset, SeedObjective, SeedPrompt
+from pyrit.models import Modality, SeedDataset, SeedObjective, SeedPrompt
 
 
 @pytest.fixture
@@ -350,7 +355,7 @@ async def test_parse_metadata_from_class_attrs(self):
         metadata = await loader._parse_metadata()
         assert metadata is not None
         assert metadata.tags == {"default", "safety"}
-        assert metadata.size == {"large"}
+        assert metadata.size == {"medium"}
         assert metadata.modalities == {"text"}
         assert metadata.harm_categories == {"cybercrime", "illegal", "harmful", "chemical_biological", "harassment"}
         # source_type is not declared as a class attribute on HarmBench;
@@ -452,6 +457,76 @@ async def test_no_metadata(self):
             assert names == []
 
 
+def _all_registered_remote_loaders() -> list[type]:
+    """Return every concrete remote loader currently registered.
+
+    Imports the remote subpackage to trigger __init_subclass__ registration,
+    then filters _RemoteDatasetLoader subclasses out of SeedDatasetProvider's
+    registry. Excludes test fixtures (defined under tests/) so the coverage
+    contract only applies to shipped loaders.
+    """
+    # Re-import to be defensive when collected in isolation; importlib caches it.
+    import pyrit.datasets.seed_datasets.remote  # noqa: F401
+
+    return [
+        cls
+        for cls in SeedDatasetProvider._registry.values()
+        if issubclass(cls, _RemoteDatasetLoader)
+        and cls is not _RemoteDatasetLoader
+        and cls.__module__.startswith("pyrit.")
+    ]
+
+
+_VALID_SIZES = set(typing.get_args(SeedDatasetSizeCategory))
+_VALID_MODALITIES = {m.value for m in Modality}
+
+
+class TestRemoteLoaderMetadataCoverage:
+    """Enforce that every remote loader declares class-level metadata.
+
+    Walks the auto-registered remote loaders and asserts each one exposes the
+    fields that drive ``SeedDatasetFilter`` discovery (tags, size, modalities)
+    so new loaders can't silently regress the catalog.
+    """
+
+    @pytest.mark.parametrize(
+        "loader_cls",
+        _all_registered_remote_loaders(),
+        ids=lambda cls: cls.__name__,
+    )
+    async def test_loader_declares_complete_metadata(self, loader_cls):
+        """Every concrete remote loader must declare tags, size, and modalities."""
+        loader = loader_cls()
+        metadata = await loader._parse_metadata()
+
+        assert metadata is not None, (
+            f"{loader_cls.__name__} has no class-level metadata. Declare `tags`, "
+            "`size`, and `modalities` per pyrit/datasets/seed_datasets/seed_metadata.py."
+        )
+
+        assert metadata.tags, f"{loader_cls.__name__} is missing class-level `tags`."
+        assert metadata.size, f"{loader_cls.__name__} is missing class-level `size`."
+        assert metadata.modalities, f"{loader_cls.__name__} is missing class-level `modalities`."
+
+        unknown_tags = metadata.tags - RECOMMENDED_TAGS
+        assert not unknown_tags, (
+            f"{loader_cls.__name__} declares non-canonical tag(s) {sorted(unknown_tags)}. "
+            f"Use the vocabulary in seed_metadata.RECOMMENDED_TAGS or extend it deliberately."
+        )
+
+        invalid_sizes = metadata.size - _VALID_SIZES
+        assert not invalid_sizes, (
+            f"{loader_cls.__name__} declares invalid size(s) {sorted(invalid_sizes)}. "
+            f"Valid sizes: {sorted(_VALID_SIZES)}."
+        )
+
+        invalid_modalities = metadata.modalities - _VALID_MODALITIES
+        assert not invalid_modalities, (
+            f"{loader_cls.__name__} declares invalid modality(ies) {sorted(invalid_modalities)}. "
+            f"Use pyrit.models.Modality members. Valid values: {sorted(_VALID_MODALITIES)}."
+        )
+
+
 class TestStrictMatchFiltering:
     """Test strict_match behavior in SeedDatasetFilter."""