Skills
Navigate
skills/team-telnyx/ai/telnyx-ai-inference-python/Gen Agent Trust Hub

telnyx-ai-inference-python

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill includes functions that process external data, which could serve as attack surfaces for indirect prompt injection.
  • Ingestion points: The skill uses client.ai.embeddings.url to crawl external websites and client.ai.summarize to process file contents (PDF, HTML, CSV, etc.) from storage buckets.
  • Boundary markers: The provided code examples do not include explicit boundary markers or instructions to ignore embedded commands in the ingested data.
  • Capability inventory: The skill interacts with the Telnyx AI APIs for summarization, chat completions, and embeddings.
  • Sanitization: Standard SDK usage assumes the underlying API handles sanitization or that the user provides safe data.
  • [COMMAND_EXECUTION]: The skill provides instructions for the user to install the vendor's library.
  • Evidence: pip install telnyx in SKILL.md.
  • [EXTERNAL_DOWNLOADS]: The skill interacts with the Telnyx API and includes examples for crawling external URLs.
  • Evidence: Example code demonstrates crawling https://example.com/resource via the Telnyx embedding service.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 04:55 PM