dialogue-audio

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references installation scripts and additional skills hosted on the official inference-sh GitHub repository and the inference.sh platform. These are established services in the AI inference ecosystem.
  • [COMMAND_EXECUTION]: The skill utilizes standard CLI tools such as npx for package management and the belt CLI for interacting with remote AI models and audio processing utilities.
  • [INDIRECT_PROMPT_INJECTION]: The skill includes an attack surface where user-provided text is interpolated into shell commands for audio generation. However, this is the core functionality of the skill, and standard usage patterns are demonstrated with instructions for natural delivery.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 05:53 PM
Security Audit — agent-trust-hub — dialogue-audio