deepgram-rate-limits
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious behavior, obfuscation, or security vulnerabilities were identified in the skill instructions or provided implementation scripts. The code follows industry-standard resilience patterns for API integration.
- [EXTERNAL_DOWNLOADS]: The skill references standard Node.js packages
p-limitand the official@deepgram/sdkfor managing API requests and concurrency. These are well-known libraries from official registries. - [INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface as it processes external audio URLs for transcription.
- Ingestion points: Audio source URLs passed to the
transcribeandtranscribeWithRetrymethods in both the TypeScript and Python implementations. - Boundary markers: Not explicitly defined in the provided implementation examples.
- Capability inventory: The skill's operations are limited to Deepgram SDK method calls for transcription and usage monitoring. There is no evidence of shell command execution, sensitive local file access, or unauthorized network exfiltration.
- Sanitization: Not present, which is standard for audio data intended for automated transcription services.
Audit Metadata