telnyx-voice-media-go

Pass

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The installation instructions include fetching the Telnyx Go SDK from the official repository at github.com/team-telnyx/telnyx-go.
  • [PROMPT_INJECTION]: The skill contains an attack surface for indirect prompt injection as it processes untrusted data for text-to-speech (the Payload field) and audio playback (the AudioURL field).
  • Ingestion points: untrusted data enters the agent context through the Payload parameter in the Speak method and the AudioURL parameter in the StartPlayback method (SKILL.md).
  • Boundary markers: No boundary markers or 'ignore embedded instructions' warnings are present in the code snippets to isolate these inputs.
  • Capability inventory: The skill is capable of performing network operations through the Telnyx API to manipulate call audio and recordings.
  • Sanitization: The provided examples do not demonstrate input validation or sanitization for the speech payload or audio URLs.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 18, 2026, 01:09 AM
Security Audit — agent-trust-hub — telnyx-voice-media-go