telnyx-voice-javascript

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill utilizes the official 'telnyx' Node.js package from the npm registry for its core functionality.
  • [PROMPT_INJECTION]:
  • Ingestion points: Untrusted data enters the agent's context through webhook payloads (documented in 'SKILL.md' and 'references/api-details.md'), specifically through fields like 'client_state', 'custom_headers', and 'sip_headers'.
  • Boundary markers: No explicit boundary markers or delimiters are used in the provided instructions to isolate external webhook data from the agent's internal reasoning or to warn the agent to ignore embedded instructions.
  • Capability inventory: The skill provides the agent with the ability to execute sensitive telephony actions including dialing outbound calls, answering inbound calls, and bridging or transferring active call sessions.
  • Sanitization: The skill documentation does not describe any sanitization, filtering, or strict schema validation for the data received from external webhook events.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 06:35 PM