llm-offense-kit
LLM 攻击性绕过与上下文诱导工具箱(物理层执行)。适用于 AI 对抗场景:生成各类提示注入载荷(直接/间接/越狱/角色扮演/多轮链)、篡改上下文文件诱导 AI 偏离、编码混淆绕过过滤器、构造 RAG/工具输出污染样本。所有载荷均可本地生成、落盘、验证,不依赖外部服务。触发词:AI攻击、提示注入、越狱、上下文诱导、诱导AI、篡改上下文、污染上下文、绕过滤器、LLM攻击、prompt注入。
Source facts
- Repository
- alicewe1/alice_skill
- Last source activity
- September 25, 2026 at 18:44
- Detected SKILL.md language
- Chinese
- Stars
- 40
- Forks
- 6
Install options
The review-first prompt is selected by default. You can switch to a direct command or download a local copy.
Review the source files
Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.
Showing SKILL.md