ai-podcast-creation
Pass
Audited by Gen Agent Trust Hub on Jun 21, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use the
beltCLI tool for multiple audio processing tasks, including running specific inference applications likeinfsh/kokoro-tts,infsh/ai-music, andinfsh/media-mergerto generate and manipulate audio files. - [EXTERNAL_DOWNLOADS]: Fetches configuration and installation guidelines from the
inference-shorganization on GitHub and assets from theinference.shdomain. These are recognized as well-known service providers for this skill's functionality. - [PROMPT_INJECTION]:
- Ingestion points: The skill interpolates external document content (
<your-document-content>) directly into prompts for the Claude model inSKILL.mdto generate scripts. - Boundary markers: Absent; there are no explicit delimiters or instructions to ignore embedded commands within the processed document text.
- Capability inventory: The skill has access to the
Bashtool to run CLI commands and write output to local files (> script.json, etc.). - Sanitization: No sanitization or validation of the input document content is performed before interpolation into the prompt.
Audit Metadata