telnyx-ai-inference-ruby

Pass

Audited by Gen Agent Trust Hub on Mar 27, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides official Ruby SDK implementation examples for Telnyx AI services, which is consistent with the vendor's intended functionality.
  • [CREDENTIALS_UNSAFE]: The skill follows secure credential management practices by retrieving the API key from an environment variable (ENV['TELNYX_API_KEY']) rather than using hardcoded secrets.
  • [EXTERNAL_DOWNLOADS]: The skill utilizes the official 'telnyx' Ruby gem installed via standard package management, which is a trusted dependency for this service.
  • [PROMPT_INJECTION]: The skill describes an interface for processing external data which constitutes a potential indirect prompt injection surface. 1. Ingestion points: messages in chat completions, URL in document embedding, and query in similarity search. 2. Boundary markers: No explicit boundary markers or 'ignore' instructions are present in the code snippets. 3. Capability inventory: The skill performs authenticated network requests to Telnyx API endpoints. 4. Sanitization: No specific input sanitization or filtering is demonstrated in the examples.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 27, 2026, 01:17 AM
Security Audit — agent-trust-hub — telnyx-ai-inference-ruby