ai-podcast-creation

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references installation instructions and images hosted on inference.sh and its associated GitHub repositories. These are treated as safe well-known service references.
  • [COMMAND_EXECUTION]: The skill uses the belt CLI tool (inference.sh official CLI) to interact with AI models for text-to-speech, music generation, and audio merging. All commands are standard usage for the documented purpose.
  • [REMOTE_CODE_EXECUTION]: The skill suggests installing the belt-sh/cli and other related skills using npx skills add. These references point to the official inference-sh organization on GitHub, which is a recognized and expected source for this skill's functionality.
  • [INDIRECT_PROMPT_INJECTION]: The skill describes a workflow where documents are passed to Claude for script generation. While this presents an ingestion surface for untrusted data, the skill includes reasonable boundary descriptions and the potential impact is limited to the generation of the audio script itself.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 05:02 AM
Security Audit — agent-trust-hub — ai-podcast-creation