ai-content-pipeline

Pass

Audited by Gen Agent Trust Hub on Apr 23, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides links to official installation guides and documentation hosted on the vendor's GitHub repository and primary domain.
  • [COMMAND_EXECUTION]: Detailed examples demonstrate how to use the authorized belt CLI tool to execute AI models and process data across different pipeline steps.
  • [PROMPT_INJECTION]: The workflow for converting blog posts to video scripts involves processing external, potentially untrusted text data, which creates a surface for indirect prompt injection. * Ingestion points: Blog content placeholders in the documentation's CLI examples (SKILL.md). * Boundary markers: None present in the example commands to isolate processed text. * Capability inventory: The skill utilizes the belt CLI to run remote AI inference tasks. * Sanitization: The provided examples do not include explicit content filtering or sanitization steps.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 23, 2026, 10:14 PM