content-repurposing

Pass

Audited by Gen Agent Trust Hub on Aug 8, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches installation instructions from the official repository at github.com/inference-sh/skills.
  • [COMMAND_EXECUTION]: Uses the 'belt' CLI tool to execute media generation tasks (images, audio, video) and social media automation, which is consistent with the skill's primary purpose.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external content such as blog posts and podcast transcripts for repurposing.
  • Ingestion points: Content provided for conversion (e.g., podcast audio, blog text).
  • Boundary markers: The provided command templates do not use specific delimiters to separate user content from instructions.
  • Capability inventory: The skill can interact with external media generation APIs and social media platforms through the 'belt' tool.
  • Sanitization: Input content is not sanitized within the skill; the system relies on the safety guardrails of the underlying AI models.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 8, 2026, 08:29 PM
Security Audit — agent-trust-hub — content-repurposing