{"slug": "dataset-ai-agent-security-failures-1000-incidents-classified", "title": "Dataset: AI agent security failures, 1000 incidents classified", "summary": "A dataset titled 'AI agent security failures' containing 1,000 classified incidents is currently inaccessible because the Hugging Face dataset viewer cannot parse its split names, throwing a SplitsNotFoundError due to a JSON parse error. The error originates from the datasets library's inability to read the dataset config, leaving the 1,000 incidents unviewable.", "body_md": "[ Datasets:](/datasets)\n\n## The dataset viewer is not available for this subset.\n\n```\nException:    SplitsNotFoundError\nMessage:      The split names could not be parsed from the dataset config.\nTraceback:    Traceback (most recent call last):\n                File \"/usr/local/lib/python3.14/site-packages/datasets/packaged_modules/json/json.py\", line 290, in _generate_tables\n                  pa_table = paj.read_json(\n                      io.BytesIO(batch), read_options=paj.ReadOptions(block_size=block_size)\n                  )\n                File \"pyarrow/_json.pyx\", line 342, in pyarrow._json.read_json\n                File \"pyarrow/error.pxi\", line 155, in pyarrow.lib.pyarrow_internal_check_status\n                File \"pyarrow/error.pxi\", line 92, in pyarrow.lib.check_status\n                  raise convert_status(status)\n              pyarrow.lib.ArrowInvalid: JSON parse error: Column() changed from object to string in row 0\n              \n              During handling of the above exception, another exception occurred:\n              \n              Traceback (most recent call last):\n                File \"/usr/local/lib/python3.14/site-packages/datasets/inspect.py\", line 286, in get_dataset_config_info\n                  for split_generator in builder._split_generators(\n                                         ~~~~~~~~~~~~~~~~~~~~~~~~~^\n                      StreamingDownloadManager(base_path=builder.base_path, download_config=download_config)\n                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n                  )\n                  ^\n                File \"/usr/local/lib/python3.14/site-packages/datasets/packaged_modules/json/json.py\", line 101, in _split_generators\n                  pa_table = next(iter(self._generate_tables(**splits[0].gen_kwargs, allow_full_read=False)))[1]\n                             ~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n                File \"/usr/local/lib/python3.14/site-packages/datasets/packaged_modules/json/json.py\", line 304, in _generate_tables\n                  batch = json_encode_fields_in_json_lines(original_batch, json_field_paths)\n                File \"/usr/local/lib/python3.14/site-packages/datasets/utils/json.py\", line 111, in json_encode_fields_in_json_lines\n                  examples = [ujson_loads(line) for line in original_batch.splitlines()]\n                              ~~~~~~~~~~~^^^^^^\n                File \"/usr/local/lib/python3.14/site-packages/datasets/utils/json.py\", line 20, in ujson_loads\n                  return pd.io.json.ujson_loads(*args, **kwargs)\n                         ~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^\n              ValueError: Expected object or value\n              \n              The above exception was the direct cause of the following exception:\n              \n              Traceback (most recent call last):\n                File \"/src/services/worker/src/worker/job_runners/config/split_names.py\", line 68, in compute_split_names_from_streaming_response\n                  for split in get_dataset_split_names(\n                               ~~~~~~~~~~~~~~~~~~~~~~~^\n                      path=dataset,\n                      ^^^^^^^^^^^^^\n                      config_name=config,\n                      ^^^^^^^^^^^^^^^^^^^\n                      token=hf_token,\n                      ^^^^^^^^^^^^^^^\n                  )\n                  ^\n                File \"/usr/local/lib/python3.14/site-packages/datasets/inspect.py\", line 340, in get_dataset_split_names\n                  info = get_dataset_config_info(\n                      path,\n                  ...<6 lines>...\n                      **config_kwargs,\n                  )\n                File \"/usr/local/lib/python3.14/site-packages/datasets/inspect.py\", line 291, in get_dataset_config_info\n                  raise SplitsNotFoundError(\"The split names could not be parsed from the dataset config.\") from err\n              datasets.inspect.SplitsNotFoundError: The split names could not be parsed from the dataset config.\n```\n\nNeed help to make the dataset viewer work? Make sure to review [how to configure the dataset viewer](https://huggingface.co/docs/hub/datasets-data-files-configuration), and [open a discussion](/datasets/gemmozero/ai-agent-security-incidents/discussions/new?title=Dataset+Viewer+issue&description=The+dataset+viewer+is+not+working.%0A%0AError+details%3A%0A%0A%60%60%60%0AException%3A++++SplitsNotFoundError%0AMessage%3A++++++The+split+names+could+not+be+parsed+from+the+dataset+config.%0ATraceback%3A++++Traceback+%28most+recent+call+last%29%3A%0A++++++++++++++++File+%22%2Fusr%2Flocal%2Flib%2Fpython3.14%2Fsite-packages%2Fdatasets%2Fpackaged_modules%2Fjson%2Fjson.py%22%2C+line+290%2C+in+_generate_tables%0A++++++++++++++++++pa_table+%3D+paj.read_json%28%0A++++++++++++++++++++++io.BytesIO%28batch%29%2C+read_options%3Dpaj.ReadOptions%28block_size%3Dblock_size%29%0A++++++++++++++++++%29%0A++++++++++++++++File+%22pyarrow%2F_json.pyx%22%2C+line+342%2C+in+pyarrow._json.read_json%0A++++++++++++++++File+%22pyarrow%2Ferror.pxi%22%2C+line+155%2C+in+pyarrow.lib.pyarrow_internal_check_status%0A++++++++++++++++File+%22pyarrow%2Ferror.pxi%22%2C+line+92%2C+in+pyarrow.lib.check_status%0A++++++++++++++++++raise+convert_status%28status%29%0A++++++++++++++pyarrow.lib.ArrowInvalid%3A+JSON+parse+error%3A+Column%28%29+changed+from+object+to+string+in+row+0%0A++++++++++++++%0A++++++++++++++During+handling+of+the+above+exception%2C+another+exception+occurred%3A%0A++++++++++++++%0A++++++++++++++Traceback+%28most+recent+call+last%29%3A%0A++++++++++++++++File+%22%2Fusr%2Flocal%2Flib%2Fpython3.14%2Fsite-packages%2Fdatasets%2Finspect.py%22%2C+line+286%2C+in+get_dataset_config_info%0A++++++++++++++++++for+split_generator+in+builder._split_generators%28%0A+++++++++++++++++++++++++++++++++++++++++%7E%7E%7E%7E%7E%7E%7E%7E%7E%7E%7E%7E%7E%7E%7E%7E%7E%7E%7E%7E%7E%7E%7E%7E%7E%5E%0A++++++++++++++++++++++StreamingDownloadManager%28base_path%3Dbuilder.base_path%2C+download_config%3Ddownload_config%29%0A++++++++++++++++++++++%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%0A++++++++++++++++++%29%0A++++++++++++++++++%5E%0A++++++++++++++++File+%22%2Fusr%2Flocal%2Flib%2Fpython3.14%2Fsite-packages%2Fdatasets%2Fpackaged_modules%2Fjson%2Fjson.py%22%2C+line+101%2C+in+_split_generators%0A++++++++++++++++++pa_table+%3D+next%28iter%28self._generate_tables%28**splits%5B0%5D.gen_kwargs%2C+allow_full_read%3DFalse%29%29%29%5B1%5D%0A+++++++++++++++++++++++++++++%7E%7E%7E%7E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%0A++++++++++++++++File+%22%2Fusr%2Flocal%2Flib%2Fpython3.14%2Fsite-packages%2Fdatasets%2Fpackaged_modules%2Fjson%2Fjson.py%22%2C+line+304%2C+in+_generate_tables%0A++++++++++++++++++batch+%3D+json_encode_fields_in_json_lines%28original_batch%2C+json_field_paths%29%0A++++++++++++++++File+%22%2Fusr%2Flocal%2Flib%2Fpython3.14%2Fsite-packages%2Fdatasets%2Futils%2Fjson.py%22%2C+line+111%2C+in+json_encode_fields_in_json_lines%0A++++++++++++++++++examples+%3D+%5Bujson_loads%28line%29+for+line+in+original_batch.splitlines%28%29%5D%0A++++++++++++++++++++++++++++++%7E%7E%7E%7E%7E%7E%7E%7E%7E%7E%7E%5E%5E%5E%5E%5E%5E%0A++++++++++++++++File+%22%2Fusr%2Flocal%2Flib%2Fpython3.14%2Fsite-packages%2Fdatasets%2Futils%2Fjson.py%22%2C+line+20%2C+in+ujson_loads%0A++++++++++++++++++return+pd.io.json.ujson_loads%28*args%2C+**kwargs%29%0A+++++++++++++++++++++++++%7E%7E%7E%7E%7E%7E%7E%7E%7E%7E%7E%7E%7E%7E%7E%7E%7E%7E%7E%7E%7E%7E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%0A++++++++++++++ValueError%3A+Expected+object+or+value%0A++++++++++++++%0A++++++++++++++The+above+exception+was+the+direct+cause+of+the+following+exception%3A%0A++++++++++++++%0A++++++++++++++Traceback+%28most+recent+call+last%29%3A%0A++++++++++++++++File+%22%2Fsrc%2Fservices%2Fworker%2Fsrc%2Fworker%2Fjob_runners%2Fconfig%2Fsplit_names.py%22%2C+line+68%2C+in+compute_split_names_from_streaming_response%0A++++++++++++++++++for+split+in+get_dataset_split_names%28%0A+++++++++++++++++++++++++++++++%7E%7E%7E%7E%7E%7E%7E%7E%7E%7E%7E%7E%7E%7E%7E%7E%7E%7E%7E%7E%7E%7E%7E%5E%0A++++++++++++++++++++++path%3Ddataset%2C%0A++++++++++++++++++++++%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%0A++++++++++++++++++++++config_name%3Dconfig%2C%0A++++++++++++++++++++++%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%0A++++++++++++++++++++++token%3Dhf_token%2C%0A++++++++++++++++++++++%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%5E%0A++++++++++++++++++%29%0A++++++++++++++++++%5E%0A++++++++++++++++File+%22%2Fusr%2Flocal%2Flib%2Fpython3.14%2Fsite-packages%2Fdatasets%2Finspect.py%22%2C+line+340%2C+in+get_dataset_split_names%0A++++++++++++++++++info+%3D+get_dataset_config_info%28%0A++++++++++++++++++++++path%2C%0A++++++++++++++++++...%3C6+lines%3E...%0A++++++++++++++++++++++**config_kwargs%2C%0A++++++++++++++++++%29%0A++++++++++++++++File+%22%2Fusr%2Flocal%2Flib%2Fpython3.14%2Fsite-packages%2Fdatasets%2Finspect.py%22%2C+line+291%2C+in+get_dataset_config_info%0A++++++++++++++++++raise+SplitsNotFoundError%28%22The+split+names+could+not+be+parsed+from+the+dataset+config.%22%29+from+err%0A++++++++++++++datasets.inspect.SplitsNotFoundError%3A+The+split+names+could+not+be+parsed+from+the+dataset+config.%0A%60%60%60%0A%0A%0Acc+%40lhoestq+%40cfahlgren1.) for direct support.\n\n# AI Agent Security Incidents 2026\n\n**1,000+ classified incidents** • Updated daily • CC BY 4.0\n\nPipeline 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.\n\n**Statistiques principales :**\n\n- 1 000+ incidents acceptés\n- 82 incidents critiques\n- Top vendors : NVIDIA (48), OpenAI (46), TensorFlow (44)\n- Top types : api_exploit, unauthorized_action, configuration_exploit, data_exfiltration, prompt_injection, sandbox_escape, slopsploit_attack_chain (découvert par le modèle)\n\nToutes les entrées ont une `source_url`\n\nvérifiable.\n\n**Dataset complet :** [https://huggingface.co/datasets/gemmozero/ai-agent-security-incidents](https://huggingface.co/datasets/gemmozero/ai-agent-security-incidents)\n\n**Code du pipeline :** [https://github.com/Legion33shadow/legion-n8n-shield](https://github.com/Legion33shadow/legion-n8n-shield)\n\nFeedback technique bienvenu (faux positifs, taxonomy, nouvelles sources).\n\nDernière mise à jour : 23 août 2026\n\n## Support this project\n\nIf you find this dataset useful, consider supporting continued development:\n[https://gemmo.gumroad.com/l/mdevxu](https://gemmo.gumroad.com/l/mdevxu)\n\n- Downloads last month\n- 178", "url": "https://wpnews.pro/news/dataset-ai-agent-security-failures-1000-incidents-classified", "canonical_source": "https://huggingface.co/datasets/gemmozero/ai-agent-security-incidents", "published_at": "2026-08-26 09:57:13+00:00", "updated_at": "2026-08-26 10:15:44.809286+00:00", "lang": "en", "topics": ["ai-safety", "ai-agents"], "entities": ["Hugging Face"], "alternates": {"html": "https://wpnews.pro/news/dataset-ai-agent-security-failures-1000-incidents-classified", "markdown": "https://wpnews.pro/news/dataset-ai-agent-security-failures-1000-incidents-classified.md", "text": "https://wpnews.pro/news/dataset-ai-agent-security-failures-1000-incidents-classified.txt", "jsonld": "https://wpnews.pro/news/dataset-ai-agent-security-failures-1000-incidents-classified.jsonld"}}