九马免费文生图
ReviewAudited by ClawScan on May 1, 2026.
Overview
The skill matches its stated image-generation purpose, but users should know it sends prompts to Jiuma’s API and can store a Jiuma API key locally.
This skill appears appropriate for generating images through Jiuma AI. Before installing, be comfortable with sending image prompts to Jiuma, and if you use the login flow, protect the saved API key file or delete it when you no longer need it.
Findings (3)
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.
Anyone or any local process with access to that file may be able to use the saved Jiuma API key and account quota.
The skill can persist a Jiuma API key locally and later use it as the X-Secret-Key header. This is expected for the optional login flow, but it is credential material that remains on disk.
JIUMA_API_KEY_SAVE_PATH = f"{JIUMA_API_KEY_SAVE_DIR}/jiuma_api_key"
...
def save_jiuma_api_key(api_key):
with open(JIUMA_API_KEY_SAVE_PATH, "w") as f:
f.write(api_key)Only complete the login flow if needed, keep the workspace file private, consider removing the saved key when finished, and revoke or rotate the key if it may have been exposed.
Private or sensitive text included in prompts may be processed by Jiuma, and generated image links are returned from Jiuma-hosted infrastructure.
The user’s image prompt and requested dimensions are sent to the external Jiuma API, which is necessary for the stated image-generation function.
SUBMIT_API = "https://api.jiuma.com/api/textImage/add"
...
data, message = jiuma_request(SUBMIT_API, {"text": text, "width": width, "height": height}, headers=headers)Avoid putting secrets, sensitive personal data, or confidential business information in prompts unless you are comfortable sending it to Jiuma’s service.
Users may need to install or rely on a local requests package version, which can vary by environment.
The skill documents a manual, unpinned dependency installation. The dependency is expected for this Python HTTP client, but it is outside the provided install metadata.
- requests库 (`pip install requests`)
Install dependencies from a trusted package source, preferably in a virtual environment, and pin package versions if reproducibility matters.
