Skills
skills/magentosh/skills/text-to-speech/Gen Agent Trust Hub

text-to-speech

Pass

Audited by Gen Agent Trust Hub on Jul 23, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill guides users to install the belt CLI tool using npx and references installation documents hosted on the official Inference.sh GitHub repository. These resources are standard for the platform's operation.
  • [COMMAND_EXECUTION]: Multiple examples demonstrate using the belt tool to run remote AI models (e.g., infsh/kokoro-tts, inworld/text-to-speech-2). These commands are restricted by the allowed-tools configuration to ensure they operate within the expected scope.
  • [PROMPT_INJECTION]: The skill facilitates passing user text to remote TTS models. This ingestion point is used for generating audio output and does not involve instructions that would be re-processed by the agent as commands, effectively mitigating typical injection risks.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 23, 2026, 06:04 PM
Security Audit — agent-trust-hub — text-to-speech