Image Generator

Generate images via BigModel APIs and send them as chat images (e.g. Feishu). Invoke when user asks to create a single picture with specific style/size.

This skill appears to implement the advertised image-generation behavior, but review before enabling: 1) Set ZHIPU_API_KEY explicitly in the agent/tool config rather than relying on the script's undocumented TOOLS.md search — the script will try to read TOOLS.md files in parent/workspace locations which could expose local secrets. 2) Be aware the script expects the requests Python package; ensure the runtime has it. 3) There's a minor bug (missing import re) which will cause the fallback file-read code to fail; that reduces risk of hidden key extraction but also indicates the code was not fully reviewed. 4) If you will run this in a production environment, inspect any TOOLS.md files in your workspace for sensitive data or remove that fallback behavior. 5) If you need greater assurance, ask the publisher for source provenance or a homepage and request they remove or document the TOOLS.md fallback. If you are uncomfortable with the undocumented file access, do not install or run the skill until it's fixed/documented.

Type: OpenClaw Skill Name: zhipu-image-generator Version: 1.0.0 The skill bundle is a functional tool for generating images via the Zhipu/BigModel API. The Python script (scripts/generate.py) correctly implements the API call to 'open.bigmodel.cn' and handles image downloads as described. While the script contains minor bugs (a missing 'import re' and an unexpanded tilde in a file path), there is no evidence of malicious intent, data exfiltration, or prompt injection attacks in the SKILL.md instructions.