text-to-speech

Pass

Audited by Gen Agent Trust Hub on Mar 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill interfaces with the inference-sh API using the infsh CLI tool.\n
  • Evidence: Example commands like infsh app run demonstrate standard usage for generating audio from text.\n
  • Security: The skill uses allowed-tools metadata to restrict the agent to only executing the infsh binary, which prevents arbitrary command injection and enforces a limited execution environment.\n- [EXTERNAL_DOWNLOADS]: The skill provides instructions for installing necessary components from the vendor's repository.\n
  • Evidence: The documentation guides the user to install the CLI and additional skills using npx skills add inference-sh/skills@agent-tools.\n
  • Verification: These references point to the official inference-sh organization and are part of the standard setup process for the vendor's verified ecosystem.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 17, 2026, 10:48 PM