xfyun-tti
Pass
Audited by Gen Agent Trust Hub on Jul 13, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXFILTRATION]: The skill communicates exclusively with the official iFlytek Spark API endpoint (
spark-api.cn-huabei-1.xf-yun.com) to perform its stated function of text-to-image generation. No unauthorized data transmission was detected. - [CREDENTIALS_UNSAFE]: The script properly handles sensitive information by requiring
XFYUN_APP_ID,XFYUN_API_KEY, andXFYUN_API_SECRETto be provided as environment variables. No credentials are hardcoded in the source code. - [PROMPT_INJECTION]: The script ingests user-provided text through the
--promptargument. While the input is interpolated directly into the JSON request body for the API, the script implements a 1000-character length constraint as a basic sanitization measure. The risk is limited to the context of the image generation model's output.
Audit Metadata