Skills
Navigate
skills/halt-catch-fire/skills/text-to-speech/Gen Agent Trust Hub

text-to-speech

Pass

Audited by Gen Agent Trust Hub on Jul 22, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the Bash tool but applies a restrictive scope through the allowed-tools configuration, limiting execution strictly to the belt command. This follow the principle of least privilege.
  • [EXTERNAL_DOWNLOADS]: The skill references installation instructions and media from inference.sh and its associated GitHub repository. These downloads are standard for utilizing the intended service and do not involve piping remote content directly to a shell.
  • [DATA_EXFILTRATION]: Authentication is handled via the belt login command, which is the expected method for service interaction. There is no evidence of unauthorized credential harvesting or sensitive data transfer to third-party domains.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 22, 2026, 07:31 AM
Security Audit — agent-trust-hub — text-to-speech