telnyx-ai-inference-go

Pass

Audited by Gen Agent Trust Hub on Mar 27, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses the official Telnyx Go SDK, which is fetched from the vendor's verified GitHub repository (github.com/team-telnyx/telnyx-go).
  • [DATA_EXFILTRATION]: Secure credential management is implemented by retrieving the API key from environment variables (os.Getenv("TELNYX_API_KEY")), avoiding the risk of hardcoded secrets.
  • [PROMPT_INJECTION]: The skill provides interfaces to process external content via AI.Embeddings.URL and AI.Summarize. This represents a functional surface for indirect prompt injection where untrusted data from remote sources could influence agent behavior.
  • Ingestion points: client.AI.Embeddings.URL and client.AI.Summarize in SKILL.md
  • Boundary markers: No delimiters or ignore-instructions warnings are present in the code examples.
  • Capability inventory: The skill can interact with the Telnyx AI Inference API to perform chat completions, transcriptions, and document searches.
  • Sanitization: No explicit content sanitization or validation is demonstrated in the documentation snippets.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 27, 2026, 01:01 AM