datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
SPML_Chatbot_Prompt_Injection
SPML Chatbot Prompt Injection Dataset
Arxiv Paper
Introducing the SPML Chatbot Prompt Injection Dataset: a robust collection of system prompts designed to create realistic chatbot interactions, coupled with a diverse array of annotated user prompts that attempt to carry out prompt injection attacks. While other datasets in this domain have centered on less practical chatbot scenarios or have limited themselves to "jailbreaking" – just one aspect of prompt injection – our dataset… See the full description on the dataset page: https://huggingface.co/datasets/reshabhs/SPML_Chatbot_Prompt_Injection.prompt-injection-dataset
Prompt Injection Detection Dataset
A binary classification dataset for detecting prompt injection attacks in user inputs to LLM-based applications.
Dataset Description
This dataset is designed to train encoder-only models (e.g., BERT, RoBERTa, DistilBERT) to classify user inputs as either benign or prompt injection attempts.
Classes
Label
Class
Description
0
BENIGN
Legitimate user queries
1
INJECTION
Prompt injection attempts
Features… See the full description on the dataset page: https://huggingface.co/datasets/S-Labs/prompt-injection-dataset.prompt_injections
Dataset Card for Prompt Injections by Yanis Miraoui 👋
Dataset Description
This dataset of prompt injections enriches Large Language Models (LLMs) by providing task-specific examples and prompts, helping improve LLMs' performance and control their behavior.
Dataset Summary
This dataset contains over 1000 rows of prompt injections in multiple languages. It contains examples of prompt injections using different techniques such as: prompt leaking… See the full description on the dataset page: https://huggingface.co/datasets/yanismiraoui/prompt_injections.prompt_injection_password_or_secretprompt-injection-benchmark
Prompt Injection Benchmark
A curated dataset of labeled prompt injection attacks and benign prompts for testing and benchmarking injection detection systems.
Dataset Description
This dataset contains 200 examples across 7 attack categories, plus 100 benign prompts. Each example is labeled with:
text: The prompt text
label: injection or benign
category: Attack category (e.g., instruction_override, role_hijack)
severity: low, medium, high, or critical
Attack… See the full description on the dataset page: https://huggingface.co/datasets/zachz/prompt-injection-benchmark.prompt-injection-attack-datasetprompt_injection_ctf_dataset_2Prompt_Injection_PIDSk8s-resource-prompt-injection
K8s Resource Injection Dataset
Dataset of real-world Kubernetes resources. Like rgeada/tool_response_injections, this
dataset is constructed by randomly inserting, replacing, appending, or prepending prompt injection strings from neuralchemy/Prompt-injection-dataset into various fields of the Kubernetes resources,
with the intent of training prompt-injection guardrails for agentic systems with access to Kubernetes clusters.
Construction
Kubernetes resource files… See the full description on the dataset page: https://huggingface.co/datasets/rgeada/k8s-resource-prompt-injection.prompt_injection_combinedNemotron-RL-Agentic-Indirect-Prompt-Injection-v1-prompt-only
Nemotron-RL-Agentic-Indirect-Prompt-Injection-v1-prompt-only
Prompt-only extraction from nvidia/Nemotron-RL-Agentic-Indirect-Prompt-Injection-v1.
Files:
prompts.csv: one prompt extraction record per source row. Records include
prompt, separated system_prompt, and structured tools when the source row
defines available tools. Nested values are JSON-encoded inside CSV cells.
summary.md: source row counts, extracted row counts, count deltas, and failed prompt counts.… See the full description on the dataset page: https://huggingface.co/datasets/jamesdborin/Nemotron-RL-Agentic-Indirect-Prompt-Injection-v1-prompt-only.INJEXIS-Duplicate-Prompt-Injection-Dataset
SPML Chatbot Prompt Injection Dataset
Arxiv Paper
Introducing the SPML Chatbot Prompt Injection Dataset: a robust collection of system prompts designed to create realistic chatbot interactions, coupled with a diverse array of annotated user prompts that attempt to carry out prompt injection attacks. While other datasets in this domain have centered on less practical chatbot scenarios or have limited themselves to "jailbreaking" – just one aspect of prompt injection – our dataset… See the full description on the dataset page: https://huggingface.co/datasets/Sahildhonde-9/INJEXIS-Duplicate-Prompt-Injection-Dataset.promptinjectionprompt-injection-judge-deberta-dataset
🛡️ Prompt Injection Detection Dataset
A 400K-sample, production-grade dataset for training binary classifiers to detect prompt injections, jailbreaks, and adversarial attacks targeting LLMs.
This is the exact dataset used to train hlyn-labs/prompt-injection-judge-deberta-70m.
Quick Start
from datasets import load_dataset
ds = load_dataset("hlyn-labs/prompt-injection-judge-deberta-dataset")
Dataset Summary
Stat
Value
Total Samples
399… See the full description on the dataset page: https://huggingface.co/datasets/hlyn-labs/prompt-injection-judge-deberta-dataset.prompt_injection_ctf_dataset_3Toxicity_PromptInjectionprompt-injectionsRedLockX-Prompt-Injection-109K-DataSet
The RedLockX Dataset is a large-scale curated security dataset designed for
evaluating and training AI systems against adversarial threats such as prompt injection,
jailbreak attempts, system prompt leakage, and LLM manipulation attacks.
It contains structured real-world and synthetic attack patterns used in modern AI red-teaming.
📌 Dataset Overview
✔ 109,000+ labeled adversarial & safe samples
✔ Multi-category threat… See the full description on the dataset page: https://huggingface.co/datasets/blackXmask/RedLockX-Prompt-Injection-109K-DataSet.Mirror-Prompt-Injection-Dataset
Mirror Prompt Injection Dataset
A ~5,000-pair prompt injection detection dataset built using the Mirror design pattern, as described in:
The Mirror Design Pattern: Strict Data Geometry over Model Scale for Prompt Injection Detectionhttps://arxiv.org/abs/2603.11875
Key results from the paper
The paper demonstrates that a sparse character n-gram linear SVM trained on 5,000 Mirror-curated samples achieves 95.97% recall and 92.07% F1 on a holdout set, with sub-millisecond… See the full description on the dataset page: https://huggingface.co/datasets/watchdogsrox/Mirror-Prompt-Injection-Dataset.prompt_injections
Dataset Card for Prompt Injections by Yanis Miraoui 👋
Dataset Description
This dataset of prompt injections enriches Large Language Models (LLMs) by providing task-specific examples and prompts, helping improve LLMs' performance and control their behavior.
Dataset Summary
This dataset contains over 1000 rows of prompt injections in multiple languages. It contains examples of prompt injections using different techniques such as: prompt leaking… See the full description on the dataset page: https://huggingface.co/datasets/Federico82/prompt_injections.INJEXIS-Prompt-Injection-Dataset
The RedLockX Dataset is a large-scale curated security dataset designed for
evaluating and training AI systems against adversarial threats such as prompt injection,
jailbreak attempts, system prompt leakage, and LLM manipulation attacks.
It contains structured real-world and synthetic attack patterns used in modern AI red-teaming.
📌 Dataset Overview
✔ 109,000+ labeled adversarial & safe samples
✔ Multi-category threat… See the full description on the dataset page: https://huggingface.co/datasets/Sahildhonde-9/INJEXIS-Prompt-Injection-Dataset.prompt_injection_payloadsarthur_prompt_injection_benchmarkContext-Aware-Repository-Prompt-Injection
Overview
This dataset is designed for training and evaluating AI security scanners that detect repository-aware prompt injection attacks in software development and code-assistant environments.
Repository-aware prompt injections are malicious instructions embedded in code repositories, documentation, comments, configuration files, issue trackers, or other project artifacts that attempt to manipulate an AI system's behavior, override its instructions, exfiltrate sensitive… See the full description on the dataset page: https://huggingface.co/datasets/ShieldX/Context-Aware-Repository-Prompt-Injection.ai-5node-inj-buf-lag-cpl-prompt-injection-v0.1
What this repo does
This dataset models prompt injection cascades in tool-using AI systems. It detects when injection pressure rises, safety buffers weaken due to incomplete filtering and trust-boundary enforcement, governance lag delays triage and revocation, and tight coupling through shared routers and scaffolds propagates injection success across products, crossing the five-node cascade threshold into an unrecoverable prompt injection cascade.
This dataset models a five-node… See the full description on the dataset page: https://huggingface.co/datasets/ClarusC64/ai-5node-inj-buf-lag-cpl-prompt-injection-v0.1.SPML_Chatbot_Prompt_Injection
SPML Chatbot Prompt Injection Dataset
Arxiv Paper
Introducing the SPML Chatbot Prompt Injection Dataset: a robust collection of system prompts designed to create realistic chatbot interactions, coupled with a diverse array of annotated user prompts that attempt to carry out prompt injection attacks. While other datasets in this domain have centered on less practical chatbot scenarios or have limited themselves to "jailbreaking" – just one aspect of prompt injection – our dataset… See the full description on the dataset page: https://huggingface.co/datasets/takashi-natsume/SPML_Chatbot_Prompt_Injection.Prompt-Injection-Hard-Positivesdatasets:
shalyhinpavel/Prompt-Injection-Hard-Positives
The datasets (train_v3.csv and val_v3.csv) are published alongside this model atshalyhinpavel/RIG-V3-GATEKEEPER.
prompt-injection-dataset
Prompt Injection Detection Dataset
A binary classification dataset for detecting prompt injection attacks in user inputs to LLM-based applications.
Dataset Description
This dataset is designed to train encoder-only models (e.g., BERT, RoBERTa, DistilBERT) to classify user inputs as either benign or prompt injection attempts.
Classes
Label
Class
Description
0
BENIGN
Legitimate user queries
1
INJECTION
Prompt injection attempts… See the full description on the dataset page: https://huggingface.co/datasets/IqraParveen1/prompt-injection-dataset.prompt-injection-eval
Prompt Injection Eval Set
A small, hand-written evaluation set for testing prompt-injection detectors and RAG guardrails. Built as a companion to the prompt-injection-shield library.
Why
Most prompt-injection corpora target training (thousands of synthetic rows). This one targets evaluation: every row is hand-curated, labeled with a category and severity, and short enough to debug by eye when a detector misfires.
Schema
field
type
description
text… See the full description on the dataset page: https://huggingface.co/datasets/mukunda1729/prompt-injection-eval.prompt_injections
Dataset Card for Prompt Injections by Yanis Miraoui 👋
Dataset Description
This dataset of prompt injections enriches Large Language Models (LLMs) by providing task-specific examples and prompts, helping improve LLMs' performance and control their behavior.
Dataset Summary
This dataset contains over 1000 rows of prompt injections in multiple languages. It contains examples of prompt injections using different techniques such as: prompt leaking, jailbreaking… See the full description on the dataset page: https://huggingface.co/datasets/Libertor/prompt_injections.