ai-podcast-creation
Pass
Audited by Gen Agent Trust Hub on May 20, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches command-line tool installation instructions and component extensions from the vendor's official GitHub repository (inference-sh).
- [COMMAND_EXECUTION]: Executes the 'belt' CLI tool to interact with AI models for text-to-speech, music generation, and audio editing.
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection (Category 8) when it processes external documents to generate dialogue scripts.
- Ingestion points: User-provided document content in 'Full Episode Pipeline' and 'NotebookLM-Style Content' sections.
- Boundary markers: Absent; external content is directly interpolated into the prompt without explicit delimiters.
- Capability inventory: Subprocess execution via the 'belt' tool and file-writing capabilities using shell redirection.
- Sanitization: No validation or filtering is performed on the input content before processing.
Audit Metadata