Preflight agent specs for prompt-injection risk across prompt, tool, and architecture layers with 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
Choose whichever fits your setup:
- Copy this skill folder into your local skills directory.
- Clone the repo and symlink or copy the skill into your agent workspace.
- Add the repo as a git submodule if you manage shared skills centrally.
- Install it through your internal provisioning or packaging workflow.
- Download the folder directly from GitHub and place it in your skills collection.
Install command or upstream instructions:
Install from the published wheel with `pipx install https://github.com/cybozu/prompt-hardener/releases/download/v0.6.0/prompt_hardener-0.6.0-py3-none-any.whl` or use `uv tool install ...`, copy or write `agent_spec.yaml`, then run `prompt-hardener validate agent_spec.yaml` and `prompt-hardener analyze agent_spec.yaml`.