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.shand its associated GitHub repositories. These are treated as safe well-known service references. - [COMMAND_EXECUTION]: The skill uses the
beltCLI 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/cliand other related skills usingnpx skills add. These references point to the officialinference-shorganization 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