Evaluating Agent Safety in Realistic, High-Risk Simulations
☆31Jul 6, 2026Updated 2 weeks ago
Alternatives and similar repositories for OpenAgentSafety
Users that are interested in OpenAgentSafety are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆23Jun 18, 2025Updated last year
- [ICML 2026] Official implementation for paper "Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Ag…☆28Jul 6, 2026Updated 2 weeks ago
- The Official Repository for Paper "HarmfulSkillBench: How Do Harmful Skills Weaponize Your Agents?"☆15May 2, 2026Updated 2 months ago
- The official implementation of the paper "AgentLAB: Benchmarking LLM Agents against Long-Horizon Attacks"☆26Jun 1, 2026Updated last month
- A Security Benchmark for Claude Code Agent Skills☆69Jul 8, 2026Updated last week
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- ☆66Jun 18, 2026Updated last month
- ☆28Jun 13, 2026Updated last month
- Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks☆88Jul 1, 2026Updated 2 weeks ago
- ☆12Apr 21, 2024Updated 2 years ago
- A summarizer for Japanese articles (but ChatGPT is better)☆10Aug 1, 2022Updated 3 years ago
- Agent Security Bench (ASB)☆271Apr 16, 2026Updated 3 months ago
- MAG-SQL: Multi-Agent Generative Approach with Soft Schema Linking and Iterative Sub-SQL Refinement for Text-to-SQL☆19Jul 10, 2025Updated last year
- Wikipedia article dataset☆12May 10, 2019Updated 7 years ago
- ☆52May 19, 2026Updated 2 months ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- The official implementation of ICLR26 poster, Pragma-VL: Towards a Pragmatic Arbitration of Safety and Helpfulness in MLLMs.☆18Mar 31, 2026Updated 3 months ago
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking …☆39Oct 23, 2024Updated last year
- [ICML 2026] An Evaluation Suite for Chain-of-Thought Controllability☆50Mar 10, 2026Updated 4 months ago
- Source code of NAACL 2025 Findings "Scaling Up Membership Inference: When and How Attacks Succeed on Large Language Models"☆16Dec 16, 2025Updated 7 months ago
- ☆29May 14, 2026Updated 2 months ago
- ☆15Jul 30, 2024Updated last year
- [ICLR 2026 Oral] Invisible Safety Threat: Malicious Finetuning for LLM via Steganography☆20Mar 22, 2026Updated 3 months ago
- A framework designed to streamline the evaluation of Membership Inference Attacks (MIA) against Large Language Models (LLMs). By leveragi…☆15Updated this week
- [ICRA2026] Official code of the paper "V2V-LLM: Vehicle-to-Vehicle Cooperative Autonomous Driving with Multimodal Large Language Models"☆17Mar 3, 2026Updated 4 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- PISmith: Reinforcement Learning-based Red Teaming for Prompt Injection Defenses☆21Updated this week
- [ICLR'26] Building a Foundational Guardrail for General Agentic Systems via Synthetic Data☆48Oct 26, 2025Updated 8 months ago
- Official repo for "ProSec: Fortifying Code LLMs with Proactive Security Alignment"☆18Feb 26, 2026Updated 4 months ago
- [ArXiv 2025] Imperceptible Jailbreaking against Large Language Models☆25Oct 7, 2025Updated 9 months ago
- A benchmark and generation framework for malicious agent skills.☆40Jun 10, 2026Updated last month
- ☆15Sep 24, 2025Updated 9 months ago
- P1-VL: Bridging Visual Perception and Scientific Reasoning in Physics Olympiads☆15Feb 11, 2026Updated 5 months ago
- ☆29Jul 12, 2026Updated last week
- ☆27Jan 23, 2024Updated 2 years ago
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- Official code for our paper "Reasoning Models Hallucinate More: Factuality-Aware Reinforcement Learning for Large Reasoning Models"☆26Oct 31, 2025Updated 8 months ago
- Official implementation of "TROJail: Trajectory-Level Optimization for Multi-Turn Large Language Model Jailbreaks with Process Rewards"☆31Updated this week
- 敬語変換タスクにおける評価用データセット☆21Nov 24, 2022Updated 3 years ago
- The source code of QueryAttack.☆27Feb 23, 2025Updated last year
- ☆149Aug 11, 2025Updated 11 months ago
- This repository contains data, code and models for contextual noncompliance.☆26Jul 18, 2024Updated 2 years ago
- ☆18May 18, 2025Updated last year