local-tts

Pass

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the voxcpm package from the Python Package Index (PyPI). It also downloads approximately 10GB of model weights from HuggingFace (openbmb/VoxCPM2). HuggingFace is a recognized and well-known service for hosting AI models.
  • [COMMAND_EXECUTION]: The skill uses shell commands to create a Python virtual environment and execute a bundled synthesis script (generate.py). These commands utilize the Bash tool to run python3, pip, and file utilities.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it processes untrusted text input to generate audio.
  • Ingestion points: Text provided via the --text flag or via stdin.
  • Boundary markers: None identified in the provided usage examples.
  • Capability inventory: The skill has access to shell execution and file reading via its allowed tools.
  • Sanitization: The skill does not document specific sanitization or filtering of input text before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 10, 2026, 03:50 AM
Security Audit — agent-trust-hub — local-tts