ai-podcast-creation
Pass
Audited by Gen Agent Trust Hub on May 28, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill demonstrates processing user-provided documents and scripts by interpolating them into LLM prompts, which creates a surface for indirect prompt injection.
- Ingestion points: The 'NotebookLM-Style Content' section provides a workflow for reading user documents into a prompt for claude-sonnet-45.
- Boundary markers: None present in the provided script examples; user content is interpolated directly into the JSON input.
- Capability inventory: The skill uses the belt CLI to execute various audio generation and media processing applications.
- Sanitization: No sanitization or validation of the input content is demonstrated in the provided workflows.
- [EXTERNAL_DOWNLOADS]: The skill references installation documentation located in the official GitHub repository of the inference-sh organization.
Audit Metadata