Ranked by Attention Score: stars gained over the last 7 complete days
12 repositories by Attention Score · Oct 27, 2026 – Nov 2, 2026 (UTC)
Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in Claude Code, Codex, and MCP skills before you install them.
dsh-purge Community · DeepSeek Harness 社区维护版：宿主兼容、状态诊断、提示词管理、更新与本机备份回滚。基于小杨 / YuJunZhiXue 的 dsh-purge。
十五个 AI 客户端的内置提示词一键替换：双击即用、可自证、改前备份、一键还原。v8.26：一键破甲全程托管（自动结束进程+注入+自动拉起）、注入步骤实时提示、写后自检回滚、托盘常驻。免装 Python 单文件 exe，完全免费开源。
针对GPT 6.0,workbuddyV4.1flash的破甲实验项目
AI Agent Identity and Access Management and Inference Firewall
Access control for AI agents. Set what Claude Code, Codex, Gemini, Cursor and any MCP server are allowed to do, review risky actions before they run, and keep every action on the record.
Runtime defense against memory poisoning in AI agents (OWASP ASI06). Drop-in for LangChain, OpenAI Agents, AutoGen, CrewAI and mem0.
Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses | 500+ Papers | Perception, Cognition, Planning, Interaction, Agentic System
Prompt-injection firewall for LLM applications — 33 input detectors, 9 output scanners, federated ed25519-signed threat-intel feed. Apache 2.0, 1040 tests, F1 96.0% with 0% false positives. Docker, GitHub Action, LangChain/LlamaIndex/CrewAI integrations.
Every practical and proposed defense against prompt injection.
Open standard for Provenance & Intent Contracts (PIC) in AI agents. Verify intent, provenance, and evidence before high-impact tool calls.
AI red teaming reports, CTF write-ups and a prompt injection reference for LLM apps and agents