telnyx-voice-gather-javascript

Pass

Audited by Gen Agent Trust Hub on Oct 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from phone callers (voice and DTMF) through AI-powered gather and assistant functions.
  • Ingestion points: Caller speech and DTMF signals are sent to the AI assistant via gatherUsingAI and startAIAssistant commands in SKILL.md.
  • Boundary markers: The instructions do not provide explicit delimiters or "ignore embedded instructions" warnings to separate caller input from the system's operational logic.
  • Capability inventory: The skill is authorized to perform call control actions (e.g., adding messages, starting/stopping AI assistants) via the Telnyx SDK. No evidence of arbitrary command execution or non-vendor network access is present.
  • Sanitization: The skill relies on the vendor's underlying AI service to interpret input; no explicit client-side sanitization or validation of the caller's speech content is shown in the examples.
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the official Telnyx Node.js SDK from the public npm registry.
  • Evidence: npm install telnyx@6.74.2 in SKILL.md.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 28, 2026, 02:19 PM