telnyx-ai-inference-javascript

Pass

Audited by Gen Agent Trust Hub on Mar 24, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the "telnyx" npm package, which is the official SDK from the verified vendor.
  • [CREDENTIALS_UNSAFE]: API key handling is performed securely using environment variables (process.env["TELNYX_API_KEY"]), avoiding the risk of hardcoded secrets.
  • [COMMAND_EXECUTION]: Basic shell commands for package installation and Node.js script execution are present but restricted to standard development workflows.
  • [PROMPT_INJECTION]: The skill exposes a surface for indirect prompt injection through its data ingestion features:
  • Ingestion points: User-provided chat messages in "createCompletion", external website content crawled via "embeddings.url", and file contents processed in "summarize".
  • Boundary markers: No explicit boundary markers or instruction-ignoring warnings are present in the documentation examples.
  • Capability inventory: The skill facilitates API calls to the Telnyx backend for generating text, creating embeddings, and summarizing documents; it does not demonstrate local file-system or OS-level execution capabilities.
  • Sanitization: Input sanitization or validation is not demonstrated within the provided code snippets.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 24, 2026, 09:56 PM