text-to-speech

Pass

Audited by Gen Agent Trust Hub on Aug 31, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references a CLI installation guide hosted on GitHub (raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md). This is a standard documentation practice for CLI-based skills.
  • [COMMAND_EXECUTION]: The skill provides numerous examples using the belt CLI (belt app run, belt app list, etc.) for text-to-speech generation. These commands are integral to the skill's primary purpose and do not show signs of malicious intent or command injection vulnerabilities.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided text for speech generation. While this is an ingestion surface, the risk is negligible as the data is passed to a specialized audio inference engine rather than being used to drive agent decision-making logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 31, 2026, 11:00 PM
Security Audit — agent-trust-hub — text-to-speech