speech-to-text

Pass

Audited by Gen Agent Trust Hub on Aug 12, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: References installation metadata and additional skills hosted on the inference-sh GitHub repository and npm registry.\n- [COMMAND_EXECUTION]: Provides instructions to install the belt-sh/cli and execute audio processing tasks using the belt command-line interface.\n- [PROMPT_INJECTION]: The skill processes audio data from external URLs, representing a surface for indirect prompt injection. Ingestion points: audio_url field in shell commands; Boundary markers: None; Capability inventory: belt CLI tool execution; Sanitization: None identified for processed audio content.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 12, 2026, 10:40 PM
Security Audit — agent-trust-hub — speech-to-text