A Security Benchmark for Claude Code Agent Skills
☆72Aug 3, 2026Updated last week
Alternatives and similar repositories for MaliciousAgentSkillsBench
Users that are interested in MaliciousAgentSkillsBench are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- SkillJect: Automating Stealthy Skill-Based Prompt Injection for Coding Agents with Trace-Driven Closed-Loop Refinement☆75Jun 11, 2026Updated 2 months ago
- Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks☆91Aug 3, 2026Updated last week
- A benchmark and generation framework for malicious agent skills.☆47Jun 10, 2026Updated 2 months ago
- The Official Repository for Paper "HarmfulSkillBench: How Do Harmful Skills Weaponize Your Agents?"☆16May 2, 2026Updated 3 months ago
- ☆22Dec 18, 2025Updated 7 months ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- AgentSentinel: An End-to-End and Real-Time Security Defense Framework for Computer-Use Agents☆35Aug 31, 2025Updated 11 months ago
- The official code for "Steering Dialogue Dynamics for Robustness against Multi-turn Jailbreaking Attacks".☆18Jun 24, 2026Updated last month
- 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。☆19Mar 16, 2026Updated 4 months ago
- Evaluating Agent Safety in Realistic, High-Risk Simulations☆33Updated this week
- Backdooring Neural Code Search☆14Sep 8, 2023Updated 2 years ago
- ToxicSkills - malicious agent skills in openclaw / clawhub / agent supply chain☆17Jun 28, 2026Updated last month
- The official implementation of the paper "AgentLAB: Benchmarking LLM Agents against Long-Horizon Attacks"☆30Jun 1, 2026Updated 2 months ago
- PISmith: Reinforcement Learning-based Red Teaming for Prompt Injection Defenses☆22Jul 17, 2026Updated 3 weeks ago
- [ICML 2026] Official implementation for paper "Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Ag…☆32Jul 31, 2026Updated 2 weeks ago
- 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.
- [ICLR 2026] Official implementation of "ChatInject: Abusing Chat Templates for Prompt Injection in LLM Agents"☆21Mar 23, 2026Updated 4 months ago
- Code repo of our paper Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis (https://arxiv.org/abs/2406.10794…☆24Jul 26, 2024Updated 2 years ago
- Official code for the paper: "Multi-User Large Language Model Agents"☆27May 11, 2026Updated 3 months ago
- Scaleable input gradient regularization☆22Jul 8, 2019Updated 7 years ago
- ☆29May 14, 2026Updated 3 months ago
- [ICML'25] MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents☆37Jul 31, 2025Updated last year
- Welcome to the official repository for Siren, a project aimed at understanding and mitigating harmful behaviors in large language models …☆15Jun 14, 2026Updated 2 months ago
- A reversible code minifier for AI. Save tokens by stripping code format in your prompt, then perfectly restore it in the responces.☆21Mar 23, 2026Updated 4 months ago
- Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency☆16Aug 6, 2025Updated last year
- 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.
- Open benchmark for AI agent security tools — prompt injection, data exfiltration, tool abuse, provenance☆24Jun 3, 2026Updated 2 months ago
- ☆158Jul 2, 2024Updated 2 years ago
- ☆40May 17, 2025Updated last year
- Accept by CVPR 2025 (highlight)☆25Jun 8, 2025Updated last year
- Code for Fast Propagation is Better: Accelerating Single-Step Adversarial Training via Sampling Subnetworks (TIFS2024)☆13Mar 29, 2024Updated 2 years ago
- [AAAI'25 (Oral)] Jailbreaking Large Vision-language Models via Typographic Visual Prompts☆211Jun 26, 2025Updated last year
- [ACL 2025] The official code for "AGrail: A Lifelong Agent Guardrail with Effective and Adaptive Safety Detection".☆44Updated this week
- [ICML 2024] Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast☆126Mar 26, 2024Updated 2 years ago
- ☆48Dec 9, 2025Updated 8 months ago
- 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.
- The official implementation of our pre-print paper "Automatic and Universal Prompt Injection Attacks against Large Language Models".☆73Oct 23, 2024Updated last year
- Automatic Jailbreaking of the Text-to-Image Generative AI Systems☆15Jun 23, 2024Updated 2 years ago
- [ICLR 2025] Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"☆70Jun 9, 2025Updated last year
- Code for our NeurIPS 2023 paper Towards Evaluating Transfer-based Attacks Systematically, Practically, and Fairly☆14Jan 22, 2024Updated 2 years ago
- Röttger et al. (2025): "MSTS: A Multimodal Safety Test Suite for Vision-Language Models"☆20Mar 31, 2025Updated last year
- ☆43Mar 24, 2026Updated 4 months ago
- ☆67May 21, 2025Updated last year