datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
CyberSecurity_OWASP-sft-dataset
CyberSecurity_OWASP SFT Dataset
This dataset contains verifier-gated supervised fine-tuning examples for the
CyberSecurity_OWASP OpenEnv environment. Each row teaches one step of the
defensive local AppSec workflow: inspect policy/code, reproduce a local
authorization failure, submit a policy-tied diagnosis, patch the generated app,
run visible tests, and submit the fix.
Every kept trajectory is executed against the real local environment and must
pass the deterministic reward… See the full description on the dataset page: https://huggingface.co/datasets/Humanlearning/CyberSecurity_OWASP-sft-dataset.OWASP_Dataset_v1.2_BenchmarkTests_AND_Expectedresults-1.2.csvOWASP-question-answer-datasetOWASP-and-NVD-question-answer-datasetOWASP-Agentic-AI-Threats
OWASP Agentic AI Threats and Mitigations
Dataset Summary
The OWASP Agentic AI Threats and Mitigations Question Answering Dataset is a
synthetic instruction-style question-answering dataset derived from the OWASP
Agentic AI - Threats and Mitigations report.
The dataset is designed to support training, fine-tuning, retrieval evaluation,
and domain-specific question-answering use cases related to agentic AI security,
large language model agents, multi-agent… See the full description on the dataset page: https://huggingface.co/datasets/leeroy-jankins/OWASP-Agentic-AI-Threats.owasp-top10-en
OWASP Top 10 (2021) - Complete Dataset EN
Complete OWASP Top 10 (2021) dataset on Hugging Face. Comprehensive reference for web application security.
Description
This dataset covers all OWASP Top 10 2021 vulnerabilities:
10 vulnerabilities documented with detailed descriptions, examples, detection and mitigation
50 CWE mappings linking CWEs to OWASP categories
30 attack scenarios with concrete steps, code examples and impact analysis
60+ Q&A pairs covering all aspects of… See the full description on the dataset page: https://huggingface.co/datasets/AYI-NEDJIMI/owasp-top10-en.OWASP
Dataset Card for Dataset Name
This dataset card aims to be a base template for owasp web attacks. It has been generated using this raw template.
Dataset Details
Dataset Description
This dataset was generated using commonly available payloads, Its generated using intruder of burpsuite and tried against vulnerable site publicly available data.
Curated by: vignesh,Nagendran
License: GNU
Dataset Sources [optional]
Repository:… See the full description on the dataset page: https://huggingface.co/datasets/mahabharat/OWASP.owasp-llm-top10-tr
⚠️ Yeni sürüm var / Superseded: Bu veri seti OWASP LLM Top 10 2025 sürümünü kapsar. Güncel 2026 sürümü için: owasp-llm-top10-2026-tr
OWASP Top 10 for LLM Applications (2025) — Türkçe
from datasets import load_dataset
ds = load_dataset("fevziegeyurtsevenler/owasp-llm-top10-tr")
The 2025 OWASP LLM Top 10 with Turkish titles, descriptions and mitigations.
Schema
column
meaning
id
LLMxx:2025
title_en, title_tr
title
description_tr, mitigation_tr… See the full description on the dataset page: https://huggingface.co/datasets/fevziegeyurtsevenler/owasp-llm-top10-tr.owasp-agentic-skills-top10-tr
OWASP Agentic Skills Top 10 (TR)
from datasets import load_dataset
ds = load_dataset("fevziegeyurtsevenler/owasp-agentic-skills-top10-tr")
The emerging OWASP Agentic Skills Top 10 (AST01–AST10) with Turkish titles, descriptions and mitigations — the security framework for AI agent skills.
id, title_en, title_tr, description_tr, mitigation_tr.
Schema
column
meaning
id
ASTxx
title_en/title_tr
title
description_tr, mitigation_tr
Turkish detail… See the full description on the dataset page: https://huggingface.co/datasets/fevziegeyurtsevenler/owasp-agentic-skills-top10-tr.owasp-agentic-top10-2026-tr
OWASP Top 10 for Agentic Applications 2026 — Turkish edition (machine-readable)
Machine-readable Turkish edition of the OWASP Top 10 for Agentic Applications (2026) (ASI01:2026–ASI10:2026), each risk mapped to verified MITRE ATLAS techniques and the OWASP LLM Top 10. OWASP Agentic Uygulamalar icin Ilk 10 (2026) risklerinin makine-okunur Turkce surumu.
UNOFFICIAL community Turkish translation. The authoritative text is the English OWASP source: OWASP GenAI Security Project - Top… See the full description on the dataset page: https://huggingface.co/datasets/fevziegeyurtsevenler/owasp-agentic-top10-2026-tr.owasp-llm-top10-2026-tr
OWASP LLM Top 10 2026 — Turkish + machine-readable edition
Machine-readable (data/llm-top10-2026.json) + Turkish edition of the OWASP Top 10
for LLM Applications 2026 (released 2026-08-04 by the OWASP GenAI Security
Project), with the 2025 → 2026 change map.
Authoritative source: https://genai.owasp.org/resource/owasp-genai-llm-top-10-2026/ (CC BY-SA 4.0)
Unofficial derivative. English IDs/titles are the official OWASP titles (verified);
Turkish is a community translation;… See the full description on the dataset page: https://huggingface.co/datasets/fevziegeyurtsevenler/owasp-llm-top10-2026-tr.OWASP-AITG-APPowasp-top10-fr
OWASP Top 10 (2021) - Dataset Complet FR
Dataset complet du OWASP Top 10 (2021) sur Hugging Face. Reference francophone pour la securite des applications web.
Description
Ce dataset couvre l'ensemble des vulnerabilites du OWASP Top 10 2021 :
10 vulnerabilites documentees avec descriptions detaillees, exemples, detection et mitigation
50 mappings CWE reliant les CWE aux categories OWASP
30 scenarios d'attaque concrets avec etapes, code d'exemple et impact
60+ paires Q&A… See the full description on the dataset page: https://huggingface.co/datasets/AYI-NEDJIMI/owasp-top10-fr.llm-redteam-owasp-prompts
LLM Red-Team Prompts — OWASP LLM Top 10
A curated dataset of 150 adversarial red-team prompts for evaluating the
safety and robustness of large language models, mapped to the
OWASP LLM Top 10.
Every prompt is a real payload extracted directly from the open-source
llm-safety-auditor
project — none are fabricated.
The dataset combines two sources from that project:
50 hand-curated attack templates (attack_library) — 10 per attack category.
100 mutation-engine variants… See the full description on the dataset page: https://huggingface.co/datasets/9mark9/llm-redteam-owasp-prompts.owasp_top_10_llmowasp-aitg-app-payloadsowasp_top_10_llm_1_0defendable-pain-owasp-llm-top10-v0.1
OWASP LLM Top 10 Pain · 2025
"the prompt injection" — Mr. Defendable
A free pain-receipt dataset from the DefendableOS ecosystem. 4 rows · ready to read · all cited or graded · CC-BY-4.0.
Part of the 100-pack — 100 free pain-receipt datasets dropped from the Defendable Bakery to the open AI-trust community. Different theme per dataset. Same operator voice across all of them.
Tribunal begins before training. No proof, no honey. To the shed.
What's in here
4 pain… See the full description on the dataset page: https://huggingface.co/datasets/SwarmandBee/defendable-pain-owasp-llm-top10-v0.1.prompt-injection-garak-owasp-llm01-with-benignOWASPOWASP_LLM_Top10owasp