Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks
☆93Aug 3, 2026Updated 3 weeks ago
Alternatives and similar repositories for skill-inject
Users that are interested in skill-inject 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
- A Security Benchmark for Claude Code Agent Skills☆74Aug 3, 2026Updated 3 weeks ago
- ☆52May 19, 2026Updated 3 months ago
- Agent Skills Enable a New Class of Realistic and Trivially Simple Prompt Injections☆22Jul 2, 2026Updated last month
- The Official Repository for Paper "HarmfulSkillBench: How Do Harmful Skills Weaponize Your Agents?"☆16May 2, 2026Updated 3 months 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.
- The official implementation of the paper "AgentLAB: Benchmarking LLM Agents against Long-Horizon Attacks"☆30Jun 1, 2026Updated 2 months ago
- Code for ICLR 2025 Failures to Find Transferable Image Jailbreaks Between Vision-Language Models☆37Jun 1, 2025Updated last year
- ☆22Jun 12, 2026Updated 2 months ago
- A benchmark and generation framework for malicious agent skills.☆56Jun 10, 2026Updated 2 months ago
- ☆30May 14, 2026Updated 3 months ago
- A research workbench for developing and testing attacks against large language models, with a focus on prompt injection vulnerabilities a…☆60Jul 24, 2026Updated last month
- Official Implementation of "ToolSafe: Enhancing Tool Invocation Safety of LLM-based Agents via Proactive Step-level Guardrail and Feedbac…☆76Mar 25, 2026Updated 5 months ago
- First formal security scanner for AI agent skills & plugins. Static analysis, supply chain verification, SBOM generation. 22 frameworks s…☆30Aug 5, 2026Updated 3 weeks ago
- ☆26May 28, 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.
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking …☆38Oct 23, 2024Updated last year
- Code&Data for the paper "Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents" [NeurIPS 2024]☆118Sep 27, 2024Updated last year
- ☆21Feb 3, 2025Updated last year
- [ICML 2025] UDora: A Unified Red Teaming Framework against LLM Agents☆39Jun 24, 2025Updated last year
- A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.☆777Jun 2, 2026Updated 2 months ago
- Evaluating Agent Safety in Realistic, High-Risk Simulations☆34Aug 10, 2026Updated 2 weeks ago
- [CCS 2024] Optimization-based Prompt Injection Attack to LLM-as-a-Judge☆41Sep 17, 2025Updated 11 months ago
- [ICML 2026] Official implementation for paper "Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Ag…☆35Jul 31, 2026Updated 3 weeks ago
- Agent Security Bench (ASB)☆292Apr 16, 2026Updated 4 months ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- AgentSentinel: An End-to-End and Real-Time Security Defense Framework for Computer-Use Agents☆37Aug 31, 2025Updated 11 months ago
- An end-to-end security evaluation framework tailored for real-world personalized agent.☆15Feb 28, 2026Updated 6 months ago
- ☆35Feb 27, 2025Updated last year
- On the Loss Landscape of Adversarial Training: Identifying Challenges and How to Overcome Them [NeurIPS 2020]☆36Jul 3, 2021Updated 5 years ago
- [ICLR 2026 Oral] Invisible Safety Threat: Malicious Finetuning for LLM via Steganography☆21Mar 22, 2026Updated 5 months ago
- [ICLR'26 Oral] RedTeamCUA: Realistic Adversarial Testing of Computer-Use Agents in Hybrid Web-OS Environments☆60Feb 9, 2026Updated 6 months ago
- ☆31Mar 11, 2026Updated 5 months ago
- ☆49Mar 18, 2026Updated 5 months ago
- A collection of judges for evaluating LLM model output for safety & toxicity with a standardized API.☆16Jan 7, 2026Updated 7 months 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.
- PISmith: Reinforcement Learning-based Red Teaming for Prompt Injection Defenses☆27Updated this week
- [NeurIPS 2025] The official implementation of the paper "DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agen…☆60Jul 16, 2026Updated last month
- ☆25Dec 18, 2025Updated 8 months ago
- Official release of code for the paper RL is a hammer and LLMs are nails A simple RL approach to stronger prompt injection attacks☆53May 6, 2026Updated 3 months ago
- Code for our ICLR 2023 paper Making Substitute Models More Bayesian Can Enhance Transferability of Adversarial Examples.☆18May 31, 2023Updated 3 years ago
- ☆36Jul 1, 2026Updated last month
- Code and data to go with the Zhu et al. paper "An Objective for Nuanced LLM Jailbreaks"☆37Jul 2, 2026Updated last month