ai-podcast-creation
Pass
Audited by Gen Agent Trust Hub on Apr 9, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill processes user-supplied text to generate podcast scripts, which is an ingestion point for untrusted data. This is a functional requirement for the NotebookLM-style feature. Ingestion points: The document content placeholder in SKILL.md. Boundary markers: Data is identified by a simple label without specific delimiters. Capability inventory: The skill uses the infsh CLI for audio generation and merging. Sanitization: No explicit validation or sanitization is provided.
- [EXTERNAL_DOWNLOADS]: The documentation references the inference.sh repository for CLI installation and suggests adding related skills using npx. These resources are associated with the platform's official ecosystem and are documented neutrally.
Audit Metadata