iflytek-hyper-tts

Pass

Audited by Gen Agent Trust Hub on Oct 26, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: All operations within the skill are consistent with its stated purpose of speech synthesis. Network communications are directed to official iFlytek API domains (xf-yun.com) using secure, standard HMAC-SHA256 authentication protocols.
  • [EXTERNAL_DOWNLOADS]: The skill requires the websocket-client package, which is a well-known and standard library available on the official Python Package Index (PyPI). This dependency is necessary for the skill's core WebSocket communication functionality.
  • [COMMAND_EXECUTION]: The skill executes a local Python script (scripts/xfei_hyper_tts.py) to perform the text-to-speech conversion. The script performs expected actions such as connecting to the service provider and writing the resulting audio data to a specified output file.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data in the form of text for synthesis, representing a data ingestion surface.
  • Ingestion points: Text provided via the --text argument or read from a file via the --text_file argument in scripts/xfei_hyper_tts.py.
  • Boundary markers: None present.
  • Capability inventory: The script performs network operations (WebSocket) and file writes (saving audio files).
  • Sanitization: The script implements a 64KB length check on input text.
  • Assessment: This surface is considered safe because the input text is treated as raw data for an audio conversion engine and is not executed or interpreted as code, nor is the output re-ingested by the agent as instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 26, 2026, 11:58 AM