skills/kuanghs/agent-skills/xfyun-tti/Gen Agent Trust Hub

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, and XFYUN_API_SECRET to be provided as environment variables. No credentials are hardcoded in the source code.
  • [PROMPT_INJECTION]: The script ingests user-provided text through the --prompt argument. 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
Risk Level
SAFE
Analyzed
Jul 13, 2026, 10:01 PM
Security Audit — agent-trust-hub — xfyun-tti