text-to-speech

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches documentation and installation guidelines from the official inference.sh GitHub repository and platform domains.
  • [COMMAND_EXECUTION]: Invokes the belt CLI tool to interact with text-to-speech models. The execution environment is appropriately restricted to the belt command via the allowed-tools configuration in the YAML frontmatter.
  • [INDIRECT_PROMPT_INJECTION]: The skill provides an interface for processing user-provided text into audio.
  • Ingestion points: User-supplied strings are passed to the --input argument of the belt command in SKILL.md.
  • Boundary markers: Input is structured within JSON objects passed to the CLI tool.
  • Capability inventory: The skill is restricted to the belt CLI tool.
  • Sanitization: Input is handled by the underlying inference.sh platform for speech synthesis.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 02:23 PM
Security Audit — agent-trust-hub — text-to-speech