content-repurposing
Pass
Audited by Gen Agent Trust Hub on May 19, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides instructions to install the vendor's CLI tool via 'npx skills add belt-sh/cli' and references installation documentation hosted on the vendor's official GitHub repository (inference-sh/skills).
- [COMMAND_EXECUTION]: Uses the 'belt' CLI tool to perform authenticated operations such as application execution and social media posting. All tool usage is consistent with the skill's stated purpose of content distribution.
- [INDIRECT_PROMPT_INJECTION]: As the skill is designed to ingest and transform long-form content (blogs, podcasts) into derivative formats, it inherently possesses an attack surface for instructions embedded in source material.
- Ingestion points: Raw text from blogs and podcast transcripts.
- Boundary markers: None explicitly defined in example command templates.
- Capability inventory: The skill uses tools to post to external platforms (Twitter/X) and generate media, creating a path from source content to public distribution.
- Sanitization: Not present in the provided templates.
Audit Metadata