Skills
skills/qu-skills/skills/speech-to-text/Gen Agent Trust Hub

speech-to-text

Pass

Audited by Gen Agent Trust Hub on Jun 12, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references the inference.sh platform and provides instructions for installing the belt CLI tool via npx. These references point to the service's official infrastructure and are required for the skill's functionality.
  • [DATA_EXFILTRATION]: The skill transmits audio data to inference.sh for processing. This is the primary intended function of the speech-to-text service and is clearly documented in the usage examples.
  • [PROMPT_INJECTION]: The skill processes untrusted audio data which is converted to text.
  • Ingestion points: Audio URLs processed via the belt app run command in SKILL.md.
  • Boundary markers: Uses JSON structure for command inputs and returns structured transcription data.
  • Capability inventory: Tool access is restricted to the belt CLI via the allowed-tools configuration.
  • Sanitization: Data is processed through an external inference engine which handles the raw audio content.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 12, 2026, 10:26 PM
Security Audit — agent-trust-hub — speech-to-text