deepgram-performance-tuning
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill provides TypeScript templates that use
execSyncto invokeffmpegfor audio format conversion and optimization. This is the intended purpose of the skill and uses standard practices for audio processing utilities. - [DATA_EXPOSURE]: Code snippets correctly demonstrate retrieving sensitive credentials like
DEEPGRAM_API_KEYandREDIS_URLfrom environment variables, which is a recommended security practice. - [EXTERNAL_DOWNLOADS]: References to external resources are limited to official Deepgram documentation and well-known public NPM registries for standard libraries.
- [INDIRECT_PROMPT_INJECTION]: While the skill processes external audio data (which could theoretically contain malicious speech), the provided logic focuses on transcription and caching without executing actions based on the transcript content, minimizing the injection risk surface.
Audit Metadata