prompt-nubaby

Nubaby prompt system for prompt augmentation, routers, dictionaries, dataset captions, prompt tags, compact prompts, video/storyboard prompt shaping, and str...

This skill appears to do what it says (prompt augmentation) and has no network calls or credential requests, but it will permanently save any prompt you tell it to "remember" into knowledge/master_recipes.json. Before installing or enabling: 1) decide whether you are comfortable having prompts (which might include PII, API keys, or sensitive text) stored on disk; 2) inspect and back up knowledge/master_recipes.json after use and delete any entries you don't want persisted; 3) consider limiting the agent's file-write capability or running the skill in a sandboxed environment; 4) the manager script has no sanitization or consent flow — avoid telling the skill to remember secrets; 5) note the content contains sexualized portrait examples (some mention ages) — verify that the skill's safety rules meet your policy needs. If you need the skill but want lower risk, ask for a version that requires explicit confirmation before writing and that strips or reviews sensitive fields before saving.

Type: OpenClaw Skill Name: prompt-nubaby Version: 1.1.0 The skill bundle is a specialized prompt augmentation system for AI image and video generation (ComfyUI/Wan/Flux). The core logic in 'scripts/manager.py' provides a simple mechanism to update a JSON knowledge base ('knowledge/master_recipes.json') with new prompt templates. While the bundle includes 'S2' safety level instructions for suggestive/mature content, it explicitly defines boundaries against illegal material, minors, and explicit sexual acts. There is no evidence of data exfiltration, malicious code execution (e.g., os.system, eval), or harmful prompt injection intended to compromise the agent or host system.