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
beltCLI 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
beltCLI to run remote AI inference tasks. * Sanitization: The provided examples do not include explicit content filtering or sanitization steps.
Audit Metadata