telnyx-voice-streaming-python

Pass

Audited by Gen Agent Trust Hub on May 8, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: Identifies a potential attack surface for indirect prompt injection as the skill handles live speech transcription intended for AI integration.
  • Ingestion points: The skill processes transcription text via webhook payloads.
  • Boundary markers: No delimiters or instructions to ignore embedded content are shown in the examples.
  • Capability inventory: The skill utilizes the Telnyx SDK to perform call actions such as forking, streaming, and transcription control.
  • Sanitization: No explicit sanitization or validation of the transcribed text is demonstrated.
  • [EXTERNAL_DOWNLOADS]: The skill installs the official telnyx Python package from a public registry.
Audit Metadata
Risk Level
SAFE
Analyzed
May 8, 2026, 06:54 PM
Security Audit — agent-trust-hub — telnyx-voice-streaming-python