Official Implementation of "ToolSafe: Enhancing Tool Invocation Safety of LLM-based Agents via Proactive Step-level Guardrail and Feedback"
☆80Mar 25, 2026Updated 6 months ago
Alternatives and similar repositories for ToolSafe
Users that are interested in ToolSafe are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [ICML 2026] Official implementation for paper "Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Ag…☆38Jul 31, 2026Updated 2 months ago
- [ACL 2025] The official code for "AGrail: A Lifelong Agent Guardrail with Effective and Adaptive Safety Detection".☆45Aug 12, 2026Updated last month
- ☆37Jun 13, 2026Updated 3 months ago
- Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks☆99Aug 29, 2026Updated last month
- The official implementation of the paper "AgentLAB: Benchmarking LLM Agents against Long-Horizon Attacks"☆42Jun 1, 2026Updated 4 months ago
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- ☆32May 14, 2026Updated 4 months ago
- ☆48May 29, 2026Updated 4 months ago
- All-in-One Safety Evaluation Framwork☆56Aug 12, 2026Updated last month
- ☆27May 12, 2026Updated 4 months ago
- A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.☆899Jun 2, 2026Updated 4 months ago
- Agent Security Bench (ASB)☆310Sep 30, 2026Updated last week
- The official code for "Steering Dialogue Dynamics for Robustness against Multi-turn Jailbreaking Attacks".☆19Jun 24, 2026Updated 3 months ago
- The official implementation of the paper "AgentDyn: Are Your Agent Security Defenses Deployable in Real-World Dynamic Environments?"☆84May 19, 2026Updated 4 months ago
- Adversarial Attack for Pre-trained Code Models☆10Jul 19, 2022Updated 4 years 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.
- ☆24Dec 18, 2025Updated 9 months ago
- ☆31Mar 11, 2026Updated 6 months ago
- ☆17Jul 2, 2026Updated 3 months ago
- ☆25Jun 12, 2026Updated 3 months ago
- [ACL'26 Main Conference] Instruction Data Selection via Answer Divergence☆25Apr 14, 2026Updated 5 months ago
- Source code for the ACL'2025 paper titled "Unveiling privacy risks in llm agent memory"☆38Dec 2, 2025Updated 10 months ago
- ☆14Feb 3, 2026Updated 8 months ago
- ☆21Jan 18, 2026Updated 8 months ago
- ☆69May 21, 2025Updated last year
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- ☆35Jul 13, 2026Updated 2 months ago
- [ICML'25] MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents☆39Jul 31, 2025Updated last year
- A curated collection of research and techniques for protecting intellectual property of large language models, including watermarking, fi…☆52Jun 10, 2026Updated 3 months ago
- offical implementation of MTSA: Multi-turn Safety Alignment for LLMs through Multi-round Red-teaming☆18Jun 2, 2025Updated last year
- Repo for the paper "Meta SecAlign: A Secure Foundation LLM Against Prompt Injection Attacks".☆71Jun 11, 2026Updated 3 months ago
- [🏆ECCV'26] Official Repo for SlowBA: An efficiency backdoor attack towards VLM-based GUI agents☆20Sep 14, 2026Updated 3 weeks ago
- ☆32Feb 11, 2026Updated 7 months ago
- [ICLR 2026 Oral] RAIN-Merging☆16Mar 9, 2026Updated 7 months ago
- ☆54May 19, 2026Updated 4 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- A Benchmark for Evaluating Safety and Trustworthiness in Web Agents for Enterprise Scenarios☆29Mar 12, 2026Updated 6 months ago
- Trace origins, shared sources, and contamination risk☆29May 27, 2026Updated 4 months ago
- Agent3σ-Canary is an evaluation framework for AI Agent security in realistic runtime environments.☆37Aug 9, 2026Updated last month
- This repo is the official implementation of “Are Your Agents Upward Deceivers?”. The paper is accepted by ICML 2026.☆24Dec 15, 2025Updated 9 months ago
- [NeurIPS 2025] The official implementation of the paper "DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agen…☆61Jul 16, 2026Updated 2 months ago
- Code to generate NeuralExecs (prompt injection for LLMs)☆27Oct 5, 2025Updated last year
- 本仓库整理公开披露的 OpenClaw 恶意 / 可疑 Skills 样本，并对其进行分类、分级与风险说明，供安全研究、平台治理和风险检测使用。☆21Mar 16, 2026Updated 6 months ago