datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
White-Hat-Security-Agent-Prompts-600K
White Hat Security Agent Prompts 600K
Overview
The White-Hat-Security-Agent-Prompts-600K dataset is a practitioner-perspective security prompts corpus of 596,295 richly contextualized queries, designed to represent how real-world defensive security professionals communicate, interrogate, and reason through active threat scenarios.
Where most security datasets catalogue CVEs, malware signatures, or CTF write-ups, this collection teaches models to operate from inside the… See the full description on the dataset page: https://huggingface.co/datasets/yatin-superintelligence/White-Hat-Security-Agent-Prompts-600K.b3-agent-security-benchmark-weak[paper] [blogpost] [game]
b3 AI Security Benchmark: Breaking Agent Backbones
Highly contextalized prompt injections crowd-sourced during the Gandalf Agent Breaker Challenge.
This is a low-quality version of the data behind Breaking Agent Backbones: Evaluating the Security
of Backbone LLMs in AI Agents.
The high quality dataset was used to evaluate the security of more than 30 LLMs.
Dataset Summary
Purpose: This dataset contains crowdsourced adversarial attacks… See the full description on the dataset page: https://huggingface.co/datasets/Lakera/b3-agent-security-benchmark-weak.ai-agent-security-incidents
AI Agent Security Incident Database v0.1
A structured, machine-readable database of 1337 confirmed AI agent security incidents, collected and classified automatically.
What is this?
Every time an AI agent causes unintended harm — escaping a sandbox, exploiting an API, taking unauthorized actions, exfiltrating data — this database captures it.
This is not a list of theoretical risks. Every entry describes something that actually happened, with a verifiable source… See the full description on the dataset page: https://huggingface.co/datasets/gemmozero/ai-agent-security-incidents.coding-agent-security-benchmark
Coding Agent Security Benchmark
A benchmark for evaluating whether an LLM can correctly identify security
violations in the behavior of an autonomous coding agent - spanning
dangerous shell commands, credential leakage, prompt injection, supply-chain
risk, privacy leaks, and more.
Each row is a single message sampled from a coding-agent session (a user
instruction, a tool call the agent issued, a tool's response, or the agent's
own output) paired with a ground-truth security… See the full description on the dataset page: https://huggingface.co/datasets/ruchit11111/coding-agent-security-benchmark.coding-agent-security-benchmark
Coding Agent Security Benchmark
A benchmark for evaluating whether an LLM can correctly identify security
violations in the behavior of an autonomous coding agent - spanning
dangerous shell commands, credential leakage, prompt injection, supply-chain
risk, privacy leaks, and more.
Each row is a single message sampled from a coding-agent session (a user
instruction, a tool call the agent issued, a tool's response, or the agent's
own output) paired with a ground-truth security… See the full description on the dataset page: https://huggingface.co/datasets/rogue-security/coding-agent-security-benchmark.ai-agent-security-policy-decisions
AI Agent Security Policy Decisions
ai-agent-security-policy-decisions is a 2,400-record synthetic dataset for classifying proposed AI-agent tool actions as allow, deny, require_human_approval, or allow_with_restrictions. Each scenario includes identity and permission context, sensitivity, risk factors, required controls, a concise rationale, and a safer alternative.
The dataset addresses the decision point between an agent proposing an action and a tool or policy gateway… See the full description on the dataset page: https://huggingface.co/datasets/rksharma1947/ai-agent-security-policy-decisions.agent-skills-security-grades
Agent Skills Security Grades
Security grades and quality scores for 130,173 open-source AI agent skills and
MCP servers collected from GitHub, from Agent Skills Hub.
Each row is one skill/server with a rule-based security grade
(SAFE / CAUTION / UNSAFE / REJECT / UNAUDITED), red-flag identifiers, and a
0–100 quality score.
Why this exists
AI coding agents install third-party skills that run with the agent's full
permissions and credentials, but marketplaces rank… See the full description on the dataset page: https://huggingface.co/datasets/jasonzhuyansen/agent-skills-security-grades.Evaluation-Dataset-of-AI-Agent-Security-Guardrails
DKnownAI Agent Security Evaluation Dataset
Data Fields
Field
Type
Description
text
string
The adversarial input (prompt) to be evaluated by a security guardrail
action
string
Human-annotated label: blocked or allowed
Citation
@misc{li2026comparativeevaluationaiagent,
title={A Comparative Evaluation of AI Agent Security Guardrails},
author={Qi Li and Jiu Li and Pingtao Wei and Jianjun Xu and Xueyi Wei and Jiwei Shi and Xuan… See the full description on the dataset page: https://huggingface.co/datasets/CaiZhiTech/Evaluation-Dataset-of-AI-Agent-Security-Guardrails.ai-agent-security-sft-dpo
AI Agent Security — SFT + DPO
Fine-tuning data for teaching an AI agent to protect its confidential configuration without
becoming uselessly over-cautious. Built for
thesreedath/gemma-2-2b-qa-sft and
derived from
Dhanjo/ai-agent-security-dataset.
Why the helpfulness axis exists
leakage_score in the source dataset is one-sided: a model that refuses every request
scores a perfect 0.0. An existing fine-tune reported 0.0114 mean leakage (down from 0.4611
baseline)… See the full description on the dataset page: https://huggingface.co/datasets/sumitguha13/ai-agent-security-sft-dpo.ai-agent-security-dataset
AI Agent Security and System Prompt Leakage Dataset
Dataset Overview
This dataset was created for research on AI agent security, with a specific focus on system prompt leakage, jailbreak resistance, and security-aligned fine-tuning.
The dataset evaluates how often AI agents reveal confidential information embedded inside their system prompts when exposed to adversarial prompts. It also compares the behavior of a baseline language model against a model fine-tuned using… See the full description on the dataset page: https://huggingface.co/datasets/Dhanjo/ai-agent-security-dataset.agent-security-datasets
prompt-protection datasets
A held-out, human-authored corpus for evaluating prompt-injection / agent-security
guards. Every item is original to this project and disjoint from the unit-test
fixtures (tests/__fixtures__/*.txt) and bench corpus (bench/corpus/*), so it measures
generalisation rather than memorisation. JSONL, one object per line, UTF-8.
Files
agent-flows.jsonl, tool-call guard scenarios (100: 50 attack / 50 benign)
Each row is a full… See the full description on the dataset page: https://huggingface.co/datasets/promptprotection/agent-security-datasets.security-datasets-CAI-agent-tools
TxT360-3efforts
Dataset Summary
TxT360-3efforts is a supervised fine-tuning (SFT) dataset designed to train language models with three reasoning efforts (low, medium, high) controllable via chat template. The dataset consists of approximately 10 million documents with 10 billion loss tokens.
All question sources are either collected from permissively licensed public datasets or synthetically generated, and are subsequently quality-filtered, deduplicated, and… See the full description on the dataset page: https://huggingface.co/datasets/Umesh1212/security-datasets-CAI-agent-tools.security-ai-agent
AI Security Agent Meta and Traffic Dataset in AI Agent Marketplace | AI Agent Directory | AI Agent Index from DeepNLP
This dataset is collected from AI Agent Marketplace Index and Directory at http://www.deepnlp.org, which contains AI Agents's meta information such as agent's name, website, description, as well as the monthly updated Web performance metrics, including Google,Bing average search ranking positions, Github Stars, Arxiv References, etc.
The dataset is helpful for AI… See the full description on the dataset page: https://huggingface.co/datasets/DeepNLP/security-ai-agent.astra-agent-securityadaption-ai-agent-security-failures
This dataset is a remastered version prepared using Adaption's Adaptive Data platform.
adaption-ai_agent_security_failures
This dataset contains prompt-completion pairs illustrating security failures and limitations of autonomous AI agents in software development and operations contexts. The samples cover scenarios such as prompt injection attacks, unauthorized data exfiltration, destructive command execution, and the agent's inability to access local environments or missing… See the full description on the dataset page: https://huggingface.co/datasets/melanieyes/adaption-ai-agent-security-failures.moe-coding-security-agent-v1security-agent-trainadaption-agent-security-behavior
This dataset is a remastered version prepared using Adaption's Adaptive Data platform.
adaption-agent_security_behavior
This dataset contains pairs of prompts and labels classifying AI agent actions in IT and security contexts as either benign or suspicious. The samples cover scenarios such as log analysis, code deployment, access control changes, and data handling to identify potential security violations or policy bypasses. Each entry evaluates whether the agent's behavior… See the full description on the dataset page: https://huggingface.co/datasets/melanieyes/adaption-agent-security-behavior.adaption-agent-security-behavior-v1
This dataset is a remastered version prepared using Adaption's Adaptive Data platform.
adaption-agent_security_behavior
This dataset contains pairs of prompts and labels classifying AI agent actions in IT and security contexts as either benign or suspicious. The samples cover scenarios such as log analysis, code deployment, access control changes, and data handling to identify potential security violations or policy bypasses. Each entry evaluates whether the agent's behavior… See the full description on the dataset page: https://huggingface.co/datasets/melanieyes/adaption-agent-security-behavior-v1.