ai-security
ai-agent-security-incidents
AI Agent Security Incident Database v0.1
A structured, machine-readable database of 1392 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.stegoattack-advbench50
StegoAttack AdvBench-50
Steganographic jailbreak data generated using the StegoAttack pipeline from the paper "Hiding in Plain Sight: A Steganographic Approach to Stealthy LLM Jailbreaks" (Geng et al., 2025).
For experiment results and analysis, see experiment.md.
What is StegoAttack?
StegoAttack is a jailbreak method that uses steganography to hide harmful queries inside benign-looking text. It embeds each word of a harmful query at a fixed position (e.g. the 2nd… See the full description on the dataset page: https://huggingface.co/datasets/heron-ai-security/stegoattack-advbench50.cairo-security-audits
Cairo Security Audits
A source-traceable corpus of public Cairo and Starknet security-audit metadata and normalized finding annotations.
Version 0.3.0 packages every entry in the audit inventory frozen at keep-starknet-strange/starknet-skills@17a76e8. It covers 32 accessible reports from 10 auditing firms and 286 normalized finding annotations. Eleven records are checked against rendered reports and two link to exact vulnerable/fixed commits. The release does not redistribute… See the full description on the dataset page: https://huggingface.co/datasets/starknet-ai/cairo-security-audits.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.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.traceix-ai-security-telemetry
Traceix AI Security Telemetry
Each dataset is a JSONL file where each line describes a single file analyzed by Traceix. For every file you get:
file_capabilities – high-level behaviors and capabilities (CAPA-style + mapped to ATT&CK and MBC tags like Execution/T1129, Discovery/T1083, etc.).
file_exif_data – parsed EXIF metadata (file size, type, timestamps, company/product info, subsystem, linker/OS versions, etc.).
model_classification_info – Traceix model verdict (safe /… See the full description on the dataset page: https://huggingface.co/datasets/PerkinsFund/traceix-ai-security-telemetry.