Generate captions (descriptions) for images, videos, and documents using ZhiPu GLM-V multimodal model series. Use this skill whenever the user wants to descr...
Security Analysis
medium confidenceThis skill looks purpose-aligned, but it runs a local captioning script and sends selected media to Zhipu using your API key.
The stated purpose is media captioning with Zhipu GLM-V, and the visible implementation builds multimodal requests to Zhipu's chat-completions endpoint for that purpose.
The skill contains strong API-only and no-fallback instructions, which are coherent with its purpose but may prevent the agent from using built-in or alternative captioning methods.
There is no installer or package setup, but normal use involves executing the included Python helper script.
The required ZHIPU_API_KEY and external API calls are proportionate for a Zhipu captioning integration, but users should expect submitted media and prompts to leave the local environment.
The artifacts do not show background persistence, privilege escalation, protected-path writes, or ongoing autonomous activity; output saving appears user-directed.
Guidance
Before installing, be comfortable with running the included Python helper, providing a ZHIPU_API_KEY, and sending selected media or media URLs to Zhipu. Use a dedicated API key, monitor usage, and avoid confidential files unless that external processing is acceptable.
Latest Release
v1.0.3
No user-visible changes in this version. - No file changes detected. - Behavior, features, and documentation remain unchanged from previous version.
More by @jaredforreal
Published by @jaredforreal on ClawHub
