deepgram-rust-text-to-speech

Pass

Audited by Gen Agent Trust Hub on Nov 4, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Recommends fetching additional domain-specific skills from the vendor's official collection using the npx skills utility.
  • [INDIRECT_PROMPT_INJECTION]: The skill provides patterns for converting text to audio, creating a potential surface for indirect prompt injection when handling external data.
  • Ingestion points: Text input parameters in speak_to_file, speak_to_stream, and speak methods in SKILL.md.
  • Boundary markers: Absent in the provided code examples.
  • Capability inventory: Local file writing via Path and network operations to Deepgram's TTS endpoints across multiple scripts.
  • Sanitization: The examples do not include explicit input validation or escaping for the synthesized text.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 4, 2026, 04:43 PM