Prompt to Drawio

Generate and edit draw.io artifacts from natural-language prompts without a frontend. Use when the user asks for prompt-to-diagram workflows that need `.draw...

This skill appears to do what it claims (generate/edit/export draw.io diagrams using an LLM), but take these precautions before installing or running it: - Be aware the CLI auto-loads the nearest .env (searches upward) by default and will populate process env vars. If you have sensitive secrets in a project .env, those may be read and (if used as input) sent to the model endpoint. Run with --no-dotenv or set DRAWIO_DOTENV_FILE explicitly to avoid accidental loading. - The tool will ingest local files and URLs you pass with --file/--url and send their content to the model provider. Do not pass files that contain secrets or sensitive data unless you trust the provider. - Check the startup configuration summary the script prints (it masks keys but reports presence) to verify which key/base URL will be used. - If you plan to run inside an agent (in-session LLM mode), prefer that mode so the script does not need an external API key. - Review and/or run the included script in a controlled environment first (no sensitive .env nearby) to confirm behavior. If you are uncomfortable with automatic .env loading, always use --no-dotenv and provide keys explicitly via secure means. If you want, I can highlight the exact lines in the script that implement .env auto-loading, dotenv precedence, and the network fetches so you can review them more easily.

Type: OpenClaw Skill Name: prompt-to-drawio Version: 0.1.0 The skill bundle provides a CLI tool for generating and editing draw.io diagrams via LLM APIs, but it includes several high-risk capabilities. Specifically, the script `scripts/prompt_to_drawio.py` performs subprocess execution (`subprocess.run`) to invoke local binaries like `drawio`, `docker`, and `gh`, and it fetches arbitrary remote content via `urllib.request.urlopen` for URL-based context ingestion. Additionally, the script implements an aggressive configuration discovery mechanism (`bootstrap_project_env`) that searches for and loads `.env` files from the current working directory up through all parent directories, which could lead to unintended secret exposure. While these features are aligned with the stated purpose of diagram generation and rendering, the combination of shell, network, and broad file access qualifies the bundle as suspicious.