Dataset: AI agent security failures, 1000 incidents classified

Datasets:

The dataset viewer is not available for this subset. #

Exception:    SplitsNotFoundError
Message:      The split names could not be parsed from the dataset config.
Traceback:    Traceback (most recent call last):
                File "/usr/local/lib/python3.14/site-packages/datasets/packaged_modules/json/json.py", line 290, in _generate_tables
                  pa_table = paj.read_json(
                      io.BytesIO(batch), read_options=paj.ReadOptions(block_size=block_size)
                  )
                File "pyarrow/_json.pyx", line 342, in pyarrow._json.read_json
                File "pyarrow/error.pxi", line 155, in pyarrow.lib.pyarrow_internal_check_status
                File "pyarrow/error.pxi", line 92, in pyarrow.lib.check_status
                  raise convert_status(status)
              pyarrow.lib.ArrowInvalid: JSON parse error: Column() changed from object to string in row 0
              
              During handling of the above exception, another exception occurred:
              
              Traceback (most recent call last):
                File "/usr/local/lib/python3.14/site-packages/datasets/inspect.py", line 286, in get_dataset_config_info
                  for split_generator in builder._split_generators(
                                         ~~~~~~~~~~~~~~~~~~~~~~~~~^
                      StreamingDownloadManager(base_path=builder.base_path, download_config=download_config)
                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                  )
                  ^
                File "/usr/local/lib/python3.14/site-packages/datasets/packaged_modules/json/json.py", line 101, in _split_generators
                  pa_table = next(iter(self._generate_tables(**splits[0].gen_kwargs, allow_full_read=False)))[1]
                             ~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.14/site-packages/datasets/packaged_modules/json/json.py", line 304, in _generate_tables
                  batch = json_encode_fields_in_json_lines(original_batch, json_field_paths)
                File "/usr/local/lib/python3.14/site-packages/datasets/utils/json.py", line 111, in json_encode_fields_in_json_lines
                  examples = [ujson_loads(line) for line in original_batch.splitlines()]
                              ~~~~~~~~~~~^^^^^^
                File "/usr/local/lib/python3.14/site-packages/datasets/utils/json.py", line 20, in ujson_loads
                  return pd.io.json.ujson_loads(*args, **kwargs)
                         ~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^
              ValueError: Expected object or value
              
              The above exception was the direct cause of the following exception:
              
              Traceback (most recent call last):
                File "/src/services/worker/src/worker/job_runners/config/split_names.py", line 68, in compute_split_names_from_streaming_response
                  for split in get_dataset_split_names(
                               ~~~~~~~~~~~~~~~~~~~~~~~^
                      path=dataset,
                      ^^^^^^^^^^^^^
                      config_name=config,
                      ^^^^^^^^^^^^^^^^^^^
                      token=hf_token,
                      ^^^^^^^^^^^^^^^
                  )
                  ^
                File "/usr/local/lib/python3.14/site-packages/datasets/inspect.py", line 340, in get_dataset_split_names
                  info = get_dataset_config_info(
                      path,
                  ...<6 lines>...
                      **config_kwargs,
                  )
                File "/usr/local/lib/python3.14/site-packages/datasets/inspect.py", line 291, in get_dataset_config_info
                  raise SplitsNotFoundError("The split names could not be parsed from the dataset config.") from err
              datasets.inspect.SplitsNotFoundError: The split names could not be parsed from the dataset config.

Need help to make the dataset viewer work? Make sure to review how to configure the dataset viewer, and open a discussion for direct support.

1,000+ classified incidents • Updated daily • CC BY 4.0

Pipeline entièrement local (Lenovo Legion, CPU only, Ollama + Llama 3.1 8B). Collecte automatique depuis NVD/CVE, GitHub Advisories, Hacker News et de multiples sources de sécurité.

Statistiques principales :

• 1 000+ incidents acceptés
• 82 incidents critiques
• Top vendors : NVIDIA (48), OpenAI (46), TensorFlow (44)
• Top types : api_exploit, unauthorized_action, configuration_exploit, data_exfiltration, prompt_injection, sandbox_escape, slopsploit_attack_chain (découvert par le modèle)

Toutes les entrées ont une source_url

vérifiable.

Dataset complet : https://huggingface.co/datasets/gemmozero/ai-agent-security-incidents

Code du pipeline : https://github.com/Legion33shadow/legion-n8n-shield

Feedback technique bienvenu (faux positifs, taxonomy, nouvelles sources).

Dernière mise à jour : 23 août 2026

Support this project #

If you find this dataset useful, consider supporting continued development: https://gemmo.gumroad.com/l/mdevxu

• Downloads last month
• 178