Laucs-sudo/Skills — reverse-engineered prompt
Reverse engineered prompt
Build me a local AI skill in this repo called local security audit. I want something I can point at my own development setup on localhost and have it review for common security problems, explain what it found in simple language, and suggest safe fixes or cleanup steps. Keep it clearly limited to local use only, so it should avoid anything that looks like scanning external systems or public targets.
Please set up the skill definition, manifest, and prompt content so the folder name and metadata stay in sync and it is easy to inspect and reuse later. The output should feel practical, with a short summary, a list of issues by severity, and concrete remediation guidance for a normal developer. If there are obvious guardrails or confirmations needed before making changes, add those too. Use the existing README as the source of truth, and look up current docs online if you need to.
Want more depth? Deep Reverse