telnyx-ai-inference-javascript

Pass

Audited by Gen Agent Trust Hub on Mar 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill uses the official telnyx npm package to interact with the Telnyx API infrastructure.
  • [SAFE]: Authentication is handled correctly through environment variables (process.env['TELNYX_API_KEY']), preventing the hardcoding of sensitive credentials.
  • [PROMPT_INJECTION]: The skill handles untrusted external data which creates a potential surface for indirect prompt injection:
  • Ingestion points: Untrusted data enters via audio transcriptions (client.ai.audio.transcribe), chat messages (client.ai.chat.createCompletion), document storage buckets (client.ai.embeddings.create), and web crawling (client.ai.embeddings.url).
  • Boundary markers: The provided code examples do not demonstrate the use of delimiters or specific instructions to ignore embedded commands.
  • Capability inventory: The skill is restricted to SDK-based API calls and does not possess capabilities for direct file system access, shell command execution, or arbitrary network requests.
  • Sanitization: No explicit sanitization or filtering of processed data is shown in the usage examples.
  • [EXTERNAL_DOWNLOADS]: The client.ai.embeddings.url method allows the processing of remote web content. This is a core feature of the service for building search indexes and does not involve the execution of remote code on the local environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 16, 2026, 10:34 AM