ai-podcast-creation
Pass
Audited by Gen Agent Trust Hub on Nov 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could contain malicious instructions.
- Ingestion points: The skill takes document content as input for script generation in the 'NotebookLM-Style Content' section.
- Boundary markers: The prompt templates use basic markers like 'Document:' but lack robust delimiters or instructions to ignore embedded commands.
- Capability inventory: The skill has the capability to write to the file system and perform network operations via the belt CLI.
- Sanitization: No validation or filtering of the input document content is performed before interpolation into the prompt.
- [EXTERNAL_DOWNLOADS]: The skill recommends installing 'belt-sh/cli' and several other skills from the 'inference-sh' GitHub organization, which are external dependencies from a third-party source.
Audit Metadata