Trojan skills in the Agent
☆14Jun 8, 2026Updated 4 months ago
Alternatives and similar repositories for SkillTrojan
Users that are interested in SkillTrojan are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆33May 14, 2026Updated 5 months ago
- ☆39Jun 13, 2026Updated 4 months ago
- BackdoorAgent is a stage-aware framework and benchmark that instruments LLM-agent workflows (planning, memory, tools) to systematically i…☆51Mar 16, 2026Updated 7 months ago
- Optimize file restoration with EaseUS Data Recovery Professional on GitHub. Advanced features for professional partition recovery and aut…☆17Jun 24, 2026Updated 4 months ago
- [NeurIPS'25] Backdoor Cleaning without External Guidance in MLLM Fine-tuning☆21Oct 13, 2025Updated last year
- 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.
- Welcome to the official repository for Siren, a project aimed at understanding and mitigating harmful behaviors in large language models …☆15Jun 14, 2026Updated 4 months ago
- The Official Repository for Paper "HarmfulSkillBench: How Do Harmful Skills Weaponize Your Agents?"☆16May 2, 2026Updated 6 months ago
- Official code repo for HazardAuditor☆21Sep 20, 2026Updated last month
- ☆60May 19, 2026Updated 5 months ago
- ☆13May 17, 2021Updated 5 years ago
- A Security Benchmark for Claude Code Agent Skills☆80Aug 3, 2026Updated 3 months ago
- An official implementation of "Rethinking Graph Backdoor Attacks: A Distribution-Preserving Perspective" (KDD 2024)☆12Sep 16, 2024Updated 2 years ago
- ☆10Apr 13, 2025Updated last year
- ☆27May 12, 2026Updated 5 months 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.
- my archlinux config☆15Jul 2, 2025Updated last year
- Publication-grade pipeline, framework and teaser figures for AI conference papers — natively editable in Visio and PowerPoint. A Claude C…☆18Updated this week
- TRACE is an agentic jailbreaking framework that can reduce attack difficulty, induce the agent to execute end-to-end attack workflows thr…☆40Oct 1, 2026Updated last month
- Auto1111 port of NVlab's adversarial purification method that uses the forward and reverse processes of diffusion models to remove advers…☆13Aug 8, 2023Updated 3 years ago
- Code for the 2025 ACL publication "ConInstruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities"☆14Nov 24, 2025Updated 11 months ago
- ICML 2024 - Self-Driven Entropy Aggregation for Byzantine-Robust Heterogeneous Federated Learning☆11Jul 16, 2024Updated 2 years ago
- Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks☆101Aug 29, 2026Updated 2 months ago
- [ICML 2026] Official implementation for paper "Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Ag…☆40Jul 31, 2026Updated 3 months ago
- ☆25Apr 8, 2026Updated 6 months 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.
- ☆14Oct 7, 2022Updated 4 years ago
- 一些大语言模型AI的提示词泄露攻击与其提示词 / Prompt Leak attact to LLM AIs and their system prompt☆31Aug 23, 2025Updated last year
- ☆12Jul 18, 2023Updated 3 years ago
- AgentSentinel: An End-to-End and Real-Time Security Defense Framework for Computer-Use Agents☆39Aug 31, 2025Updated last year
- Agentic skills for vulnerability detection.☆24Jul 17, 2026Updated 3 months ago
- Evaluating Agent Safety in Realistic, High-Risk Simulations☆40Aug 10, 2026Updated 2 months ago
- 云音乐用户信息可视化☆14Nov 18, 2022Updated 3 years ago
- ☆30Jul 29, 2026Updated 3 months ago
- A low-entropy shellcode executor that encodes shellcode bytes into common English words, with anti-debugging capabilities.☆21Aug 10, 2025Updated last year
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- [ACM MM-2021] WePerson: learning a generalized re-identification model from all-weather virtual data☆11May 23, 2023Updated 3 years ago
- Code of FedSSP: Federated Graph Learning with Spectral Knowledge and Personalized Preference (NeurIPS24)☆12Dec 23, 2025Updated 10 months ago
- Repository for 2030 project☆15Dec 29, 2025Updated 10 months ago
- RLCDAlignBench: 44 alignment-failure detection benchmarks and code for 'Just Ask Jev' (RLCD zero-shot detector of AI alignment failures)☆31Sep 25, 2026Updated last month
- ☆17Jul 2, 2026Updated 4 months ago
- ☆28Jan 24, 2024Updated 2 years ago
- 提供一个极简的服务器使用介绍，为初入AI科研的同学提供些许帮助，更快上手。☆20Jul 9, 2025Updated last year