sherpa-onnx-tts

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches pre-compiled executable binaries and voice models from the official GitHub releases of the k2-fsa/sherpa-onnx project repository.
  • [COMMAND_EXECUTION]: Executes the local 'sherpa-onnx-offline-tts' binary using the 'spawnSync' method to process text into audio files.
  • [COMMAND_EXECUTION]: Dynamically modifies environment variables such as 'LD_LIBRARY_PATH', 'DYLD_LIBRARY_PATH', and 'PATH' at runtime to ensure the runtime's shared libraries are correctly resolved by the operating system.
  • [PROMPT_INJECTION]: The skill ingests untrusted text data and passes it to the synthesis engine, creating a surface for indirect prompt injection.
  • Ingestion points: The main text argument passed to the 'sherpa-onnx-tts' script (bin/sherpa-onnx-tts).
  • Boundary markers: Absent; the input text is not wrapped in delimiters or accompanied by instructions to ignore embedded commands.
  • Capability inventory: The skill can spawn subprocesses ('spawnSync') and interact with the file system ('fs.mkdirSync', 'fs.readdirSync').
  • Sanitization: No evidence of validation or filtering for the input text before it is passed to the synthesis binary.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 06:53 AM