ifly-speed-transcription

Pass

Audited by Gen Agent Trust Hub on Apr 4, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes a Python script (scripts/transcribe.py) to automate the transcription workflow, which includes file management and API requests.
  • [DATA_EXFILTRATION]: Audio data provided by the user is uploaded to iFLYTEK's official processing servers (upload-ost-api.xfyun.cn) as required for the transcription service to function.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it processes external audio files and returns the transcribed text to the agent, potentially allowing spoken instructions to influence agent behavior.
  • Ingestion points: Audio files provided to the transcribe.py script via the file_path argument.
  • Boundary markers: The output text is returned to the agent without specific delimiters or isolation instructions.
  • Capability inventory: The skill uses the requests library to perform network operations and has read access to audio files on the local filesystem.
  • Sanitization: There is no sanitization or filtering of the transcribed text before it is presented to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 4, 2026, 05:17 AM
Security Audit — agent-trust-hub — ifly-speed-transcription