qwencloud-image-generation

[QwenCloud] Generate and edit images using Wan and Qwen Image models. Supports text-to-image, image editing (style transfer, subject consistency, text render...

Before installing or invoking this skill: 1) Expect to provide a QwenCloud/DashScope API key (DASHSCOPE_API_KEY) — the skill will not work without it even though the manifest lists none. 2) Review the included scripts (qwencloud_lib.py, image_lib.py, gossamer.py, image.py) because they load .env files from the current directory or repo root and may write files under the repo (e.g., .agents/state.json) or suggest appending to agent config files; run them only if you trust the repository. 3) Do not paste your real API key into chat; follow the SKILL.md advice to use a .env with a placeholder and set the real key in your environment. 4) If you need stronger isolation, run the scripts in a throwaway/VM/container or inspect/execute them manually rather than allowing an agent to run them automatically. 5) Ask the skill author or maintainer to update the registry metadata to declare DASHSCOPE_API_KEY and any other required env vars and to clearly document which files the skill will read or modify — that will resolve the primary incoherence noted here.

Type: OpenClaw Skill Name: qwencloud-image-generation Version: 0.2.0 The skill bundle is a legitimate tool for generating and editing images via the QwenCloud/DashScope API. It contains well-structured Python scripts (image.py, qwencloud_lib.py) that handle API authentication, image processing, and local file uploads to Alibaba Cloud OSS as required for the service. The SKILL.md includes proactive security instructions directing the AI agent to never reveal API keys in plaintext. While it includes an update-check mechanism (gossamer.py) that prompts for the installation of a sibling skill via 'npx skills add', this behavior is consistent with the OpenClaw ecosystem's dependency management and lacks malicious intent.