telnyx-ai-assistants-javascript

Pass

Audited by Gen Agent Trust Hub on Mar 27, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill utilizes the official telnyx npm package, which is a verified vendor resource for the Telnyx platform.
  • [SAFE]: API credentials are correctly handled using environment variables (process.env['TELNYX_API_KEY']), which is a standard security practice for protecting sensitive tokens.
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted data which serves as a surface for indirect prompt injection.
  • Ingestion points: SKILL.md (specifically within client.ai.assistants.chat content and client.ai.assistants.create instructions).
  • Boundary markers: Not present; the skill does not implement specific delimiters to separate user data from system instructions.
  • Capability inventory: SKILL.md (API methods for assistant interaction, tool testing, and SMS messaging).
  • Sanitization: None observed; input data is passed directly to the API methods as demonstrated in the examples.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 27, 2026, 01:16 AM
Security Audit — agent-trust-hub — telnyx-ai-assistants-javascript