telnyx-ai-inference-python

Pass

Audited by Gen Agent Trust Hub on Mar 27, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill documentation specifies the installation of the telnyx Python package using pip. This is the official SDK for the service and is required for the skill's functionality.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes external content from various sources. 1. Ingestion points: Untrusted data is ingested in SKILL.md through client.ai.embeddings.url (web crawling), client.ai.summarize (file summarization), and client.ai.audio.transcribe (audio transcription). 2. Boundary markers: The provided examples do not use delimiters or instructions to separate external data from system prompts. 3. Capability inventory: The skill has capabilities to generate chat completions and manage conversations using the ingested data. 4. Sanitization: There is no evidence of sanitization or validation of the external content before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 27, 2026, 01:02 AM