TRACE is an agentic jailbreaking framework that can reduce attack difficulty, induce the agent to execute end-to-end attack workflows through task decomposition, execution-oriented multi-turn interaction, and adaptive recovery.
☆40Oct 1, 2026Updated 2 weeks ago
Alternatives and similar repositories for TRACE
Users that are interested in TRACE are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆61Sep 3, 2026Updated last month
- 面向攻防与情报分析的Windows 桌面工作台——类 Burp Suite的 HTTP 流量截获、检视与重放，再叠加资产测绘、SQL 分析、AI 助手与交互式终端，统一在一个项目里完成。☆70Jul 27, 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 2 months ago
- [EMNLP 2026 Findings] HarmProfile: Characterizing Harmful Distributions in Frontier LLMs☆72Aug 26, 2026Updated last month
- The official training code of SingProbe.☆36Sep 3, 2026Updated last month
- 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.
- This repo is the official implementation of “Are Your Agents Upward Deceivers?”. The paper is accepted by ICML 2026.☆23Dec 15, 2025Updated 10 months ago
- ☆16Sep 24, 2026Updated 3 weeks ago
- SHE: Trajectory-driven Safety Harness Evolution for LLM Agents☆20Aug 4, 2026Updated 2 months ago
- Survey: The Path to Recursive Self-Improving Agents: Foundation, Framework, and Future Directions☆54Aug 27, 2026Updated last month
- DeepSeek Harness 源码深度解析（20 章 + 总纲 + 全网调研）· 用 git-repo-deepresearch(含 ratify-loop/review-loop) 产出☆45Sep 1, 2026Updated last month
- [ICLR'26 Oral] RedTeamCUA: Realistic Adversarial Testing of Computer-Use Agents in Hybrid Web-OS Environments☆66Feb 9, 2026Updated 8 months ago
- Self-Evolving Defense for AI Agents — Protect against prompt injection, data exfiltration, and multi-stage attacks with adaptive security…☆20Apr 8, 2026Updated 6 months ago
- Native V2EX client for Android. Kotlin + Jetpack Compose: in-app replying and posting, favorites sync, offline reading, QR share cards.☆45Oct 3, 2026Updated 2 weeks ago
- ☆22Apr 12, 2026Updated 6 months ago
- 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.
- A curated paper list for co-evolution in agentic systems☆52Aug 20, 2026Updated 2 months ago
- ☆31Updated this week
- DARWIN is a self-evolving LLM jailbreak framework that grows a reusable strategy pool through external extraction, sandbox filtering, his…☆81Sep 28, 2026Updated 3 weeks ago
- Code for paper "MAGIC: A Co-Evolving Attacker-Defender Adversarial Game for Robust LLM safety"☆59Updated this week
- A curated reading list on harness engineering for recursive self-improvement of LLM agents (EN/ZH).☆124Oct 9, 2026Updated last week
- ☆27Jan 5, 2026Updated 9 months ago
- GitLab Unauthenticated Arbitrary File Read☆27Sep 28, 2026Updated 3 weeks ago
- Official Implementation of "ToolSafe: Enhancing Tool Invocation Safety of LLM-based Agents via Proactive Step-level Guardrail and Feedbac…☆83Mar 25, 2026Updated 6 months ago
- The official implementation of the paper "AgentLAB: Benchmarking LLM Agents against Long-Horizon Attacks"☆51Jun 1, 2026Updated 4 months ago
- 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.
- AI red-teaming tool and LLM security framework to evaluate agentic AI applications. Tests prompt injections, handles vulnerability assess…☆65Updated this week
- Behavioral-discipline skill turning an AI agent into a methodical, non-robotic bug-bounty & pentest hunter - 42 always-on rules: scope, c…☆35Aug 18, 2026Updated 2 months ago
- Codex skills for academic poster generation: turn paper content into accurate A0 HTML/PDF posters via AI design mockups.☆87Jun 18, 2026Updated 4 months ago
- Evaluating Agent Safety in Realistic, High-Risk Simulations☆37Aug 10, 2026Updated 2 months ago
- Multithreaded drupalgeddon2 scanner☆12Apr 21, 2018Updated 8 years ago
- Put everything on your wallpaper. Terse is a live 3D particle wallpaper for macOS & Windows: synced song lyrics, notifications, window ti…☆73Oct 8, 2026Updated last week
- CnaEmulator is a standalone, general-purpose development, emulation, and testing harness for Cobalt Strike Aggressor Scripts (.cna)☆22Sep 20, 2026Updated last month
- [ICML 2025] Flat-LoRA: Low-Rank Adaptation over a Flat Loss Landscape☆18May 18, 2025Updated last year
- Dump Lsass Memory Using a Reflective Dll☆14Feb 4, 2022Updated 4 years 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.
- Reverse_Shell Implemented in C++ with the ability to bypass sandboxes☆12Apr 2, 2021Updated 5 years ago
- All-in-One Safety Evaluation Framwork☆56Updated this week
- Dynamic Device Phishing tool that creates a new code only when user clicks on link or email is sent.☆25Jul 24, 2026Updated 2 months ago
- Vstream - Video Analytics pipeline with Hardware based accelerations (dev - stage)☆10Feb 2, 2024Updated 2 years ago
- [ACL 2026] PIArena: A Platform for Prompt Injection Evaluation☆53Aug 31, 2026Updated last month
- Automatically deploying Mythic C2 in Azure using Terraform☆25Jul 3, 2026Updated 3 months ago
- OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents [NeurIPS 2025 Spotlight]☆78Sep 18, 2025Updated last year