针对提示注入风险的预检代理规范，涵盖提示层、工具层和架构层，使用 Prompt Hardener
Describe an agent in agent_spec.yaml, run deterministic prompt-injection analysis, generate mitigations, and validate defenses before rollout.
Prerequisites
Python 3, pipx or uv optional
Installation
Use the upstream install or setup path that matches your environment:
- pipx install https://github.com/1991513ccie-png/skills
- Recommended if you already use uv for Python tooling.
- uv tool install https://github.com/1991513ccie-png/skills
- pip install https://github.com/1991513ccie-png/skills
Requirements and caveats from upstream:
- Deterministic first: init, validate, analyze, report, and diff do not require an LLM API key
- Use this if you prefer a standard Python environment.
Basic usage or getting-started notes:
- run deterministic security analysis across prompt, tool, and architecture layers
- Choose the installation method that fits how you want to use Prompt Hardener.
- ### Using pipx
- Source: https://github.com/1991513ccie-png/skills
- Extracted from upstream docs: https://raw.githubusercontent.com/cybozu/prompt-hardener/HEAD/README.md
Documentation
- https://github.com/1991513ccie-png/skills
