by jalvarezz13 · LLM 插件 · ★ 9
prompt.fail Welcome to prompt.fail, a project dedicated to exploring and documenting techniques for prompt injection in large language models (LLMs). Our mission is to enhance the security and robustness of LLMs by identifying and understanding how malicious prompts can manipulate these models. By sharing and analyzing these techniques, we aim to build a community that contributes to the development of more resilient AI systems.
| Stars | 9 |
| Forks | 1 |
| Language | TypeScript |
| Category | LLM 插件 |
| License | GPL-3.0 |
| Quality Score | 38/100 |
| Open Issues | 7 |
| Last Updated | 2026-04-20 |
| Created | 2024-07-06 |
| Platforms | claude-code, node |
| Est. Tokens | ~60k |
These tools work well together with prompt.fail for enhanced workflows:
Explore other popular llm 插件 tools:
prompt.fail is prompt.fail explores prompt injection techniques in large language models (LLMs), providing examples to improve LLM security and robustness.. It is categorized as a LLM 插件 with 9 GitHub stars.
prompt.fail is primarily written in TypeScript. It covers topics such as anthropic, claude, gpt.
You can find installation instructions and usage details in the prompt.fail GitHub repository at github.com/jalvarezz13/prompt.fail. The project has 9 stars and 1 forks, indicating an active community.
prompt.fail is released under the GPL-3.0 license, making it free to use and modify according to the license terms.