ai-content-pipeline

Pass

Audited by Gen Agent Trust Hub on Jun 12, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill documentation includes instructions for installing the belt CLI and other related skills using npx. These downloads target the belt-sh and inference-sh namespaces, which are the official sources for the tools and platform described in the skill.
  • [COMMAND_EXECUTION]: The provided workflows contain numerous bash command examples using the belt tool to orchestrate data flow between different AI models. These commands are the primary intended functionality of the skill and operate within the scope of the inference service.
  • [REMOTE_CODE_EXECUTION]: The skill recommends setup steps involving npx to download and execute the belt CLI utility. This is a standard installation method for the platform's tooling and is performed via the vendor's official package identifiers.
  • [PROMPT_INJECTION]: The skill examples demonstrate passing outputs from one model as inputs to another, such as using LLM-generated text as a prompt for speech or video generation. While this represents a data ingestion surface, it is a core feature of the pipeline and does not contain malicious injection patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 12, 2026, 10:27 PM
Security Audit — agent-trust-hub — ai-content-pipeline