[ICML 2026] Official implementation for paper "Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Agents"
☆40Jul 31, 2026Updated 3 months ago
Alternatives and similar repositories for ToolShield
Users that are interested in ToolShield are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- “ToolHazard: Scalable Red Teaming of LLM Agents via Adversarial Tool-Interactive Environment and Task Synthesis”☆15Aug 18, 2026Updated 3 months ago
- The Official Repository for Paper "HarmfulSkillBench: How Do Harmful Skills Weaponize Your Agents?"☆16May 2, 2026Updated 6 months ago
- Your agent is powerful but it doesn't know you. VibeLens visualizes agent sessions, personalizes your agents, provides dashboard analytic…☆21Oct 11, 2026Updated last month
- ICLR 206☆15Aug 18, 2026Updated 3 months ago
- AgentAlign: Navigating Safety Alignment in the Shift from Informative to Agentic Large Language Models☆14Jun 2, 2025Updated last year
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- [CVPR'26] SafeGRPO: Self-Rewarded Multimodal Safety Alignment via Rule-Governed Policy Optimization☆23Feb 19, 2026Updated 9 months ago
- Kelp is a novel plug-in framework that enables streaming risk detection within the LM generation pipeline.☆12Oct 20, 2025Updated last year
- ☆15Jan 30, 2026Updated 9 months ago
- Evaluating Agent Safety in Realistic, High-Risk Simulations☆43Aug 10, 2026Updated 3 months ago
- [EMNLP 2026] StepGuard: Learning Step-Level Guardrails with Scalable Supervision and Safety-Utility Balancing☆15Sep 26, 2026Updated last month
- [ACL 2026] PIArena: A Platform for Prompt Injection Evaluation☆57Aug 31, 2026Updated 2 months ago
- Code for ICCV2025 paper——IDEATOR: Jailbreaking and Benchmarking Large Vision-Language Models Using Themselves☆18Jul 11, 2025Updated last year
- ☆15Sep 14, 2026Updated 2 months ago
- Accept by CVPR 2025 (highlight)☆27Jun 8, 2025Updated last year
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- [NeurIPS 2025] The official implementation of the paper "DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agen…☆62Jul 16, 2026Updated 4 months ago
- Agent Data Injection (ADI) Attacks☆16Jul 13, 2026Updated 4 months ago
- TRACE is an agentic jailbreaking framework that can reduce attack difficulty, induce the agent to execute end-to-end attack workflows thr…☆41Oct 1, 2026Updated last month
- ☆27Jan 5, 2026Updated 10 months ago
- [ICLR'26 Oral] RedTeamCUA: Realistic Adversarial Testing of Computer-Use Agents in Hybrid Web-OS Environments☆67Feb 9, 2026Updated 9 months ago
- Repo for the paper "Defending Against Prompt Injection With a Few DefensiveTokens"☆19Nov 10, 2025Updated last year
- ☆86Mar 30, 2025Updated last year
- Official Repo for the paper "SecPO: Principled Adversarial Training for Prompt Injection Security"☆14Nov 5, 2026Updated last week
- ☆168Aug 11, 2025Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- SkillJect: Automating Stealthy Skill-Based Prompt Injection for Coding Agents with Trace-Driven Closed-Loop Refinement☆82Jun 11, 2026Updated 5 months ago
- The official implementation of the paper "AgentLAB: Benchmarking LLM Agents against Long-Horizon Attacks"☆55Jun 1, 2026Updated 5 months ago
- ☆34May 14, 2026Updated 6 months ago
- LLM-MemoryInspector is a Python-based toolkit designed to explore how LLMs memorize and retrieve MovieLens-1M specific information using …☆10Mar 21, 2026Updated 7 months ago
- Agent Skills Enable a New Class of Realistic and Trivially Simple Prompt Injections☆24Jul 2, 2026Updated 4 months ago
- Precision Knowledge Editing (PKE): A novel method to reduce toxicity in LLMs while preserving performance, with robust evaluations and ha…☆14Nov 26, 2024Updated last year
- ☆63May 19, 2026Updated 5 months ago
- The official training code of SingProbe.☆35Sep 3, 2026Updated 2 months ago
- A benchmark and generation framework for malicious agent skills.☆67Nov 2, 2026Updated 2 weeks ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- ☆20Nov 19, 2025Updated 11 months ago
- ☆10Oct 7, 2026Updated last month
- ☆21Feb 6, 2026Updated 9 months ago
- ☆31May 14, 2025Updated last year
- ☆28Nov 4, 2026Updated 2 weeks ago
- ATBench: A Diverse and Realistic Agent Trajectory Benchmark for Safety Evaluation and Diagnosis☆48Sep 15, 2026Updated 2 months ago
- The official code of On-Policy Self-Evolution via Failure Trajectories for Agentic Safety Alignment☆30Oct 29, 2026Updated 2 weeks ago
Are these results useful?