九马AI免费图生视频
PassAudited by ClawScan on May 1, 2026.
Overview
This appears to be a purpose-aligned Jiuma image-to-video helper, but it sends selected images/prompts to Jiuma and can store a Jiuma API key locally.
This skill is reasonable for generating videos from images with Jiuma AI. Before installing, be comfortable with uploading the selected images/prompts to Jiuma and with the optional login flow saving a Jiuma API key locally for later reuse.
Findings (2)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Images and prompts you provide for video generation may be uploaded to Jiuma's service.
The skill opens user-supplied local image files and submits them, along with prompt data, to Jiuma's remote API. This matches the image-to-video purpose but is an external provider data flow.
SUBMIT_API = "https://api.jiuma.com/api/imageVideo/add" ... f = open(image_str, 'rb') ... jiuma_request(SUBMIT_API, data=request_data, headers=headers, files=image_files)
Use only images and prompts you are comfortable sending to Jiuma, and review Jiuma's privacy/retention terms if the content is sensitive.
After login, a Jiuma API key may remain on disk and could be reused by this or other local Jiuma tools running as the same user.
The login flow stores and later reads a Jiuma API key from a local plaintext file. This is expected for continued API use, but it is persistent credential handling.
JIUMA_API_KEY_SAVE_PATH = f"{JIUMA_API_KEY_SAVE_DIR}/jiuma_api_key" ... def save_jiuma_api_key(api_key): ... f.write(api_key) ... def get_jiuma_api_key(): ... api_key = f.read()Log in only if you want persistent Jiuma access, protect the workspace file permissions, and delete or rotate the key if you no longer want the skill to use it.