text-to-speech
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides code templates that define an interface for processing external text through a Text-to-Speech engine.
- Ingestion points: The text parameter within the convert and convert_stream methods in SKILL.md serves as the entry point for data.
- Boundary markers: The provided code snippets do not include explicit delimiters or instructions to ignore embedded commands within the input text.
- Capability inventory: The code examples involve network requests to api.sarvam.ai and local file writing using functions like save and writeFile.
- Sanitization: No explicit sanitization or validation of the input text is shown in the example code.
- [EXTERNAL_DOWNLOADS]: The skill documentation references and requires the installation of the official sarvamai client libraries for Python and Node.js to function.
Audit Metadata