text-to-speech

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions to download the belt CLI tool and related skills from inference.sh and GitHub repositories. These are well-known services for the domain of AI inference tools and are documented for user setup.
  • [COMMAND_EXECUTION]: The instructions include standard CLI commands for the belt tool (e.g., belt login, belt app run) to perform text-to-speech inference. These are routine operations for an AI agent performing developer or media tasks.
  • [DATA_EXPOSURE_&_EXFILTRATION]: The skill mentions fetching voice lists from api.inworld.ai. This is a legitimate API call to a well-known AI voice service and does not involve exfiltrating sensitive local data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 02:19 PM
Security Audit — agent-trust-hub — text-to-speech