telnyx-ai-assistants-ruby
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill documents the use of the official Telnyx Ruby SDK (
telnyxgem). All demonstrated operations, including assistant management and SMS capabilities, are standard features of the vendor's platform. - [INDIRECT_PROMPT_INJECTION]: The skill provides methods for processing untrusted user input, which is a standard surface for indirect prompt injection in AI assistant integrations.
- Ingestion points: Untrusted data enters the agent context through the
contentparameter in thechatmethod and theinstructionsparameter in thecreatemethod (SKILL.md). - Boundary markers: The documentation does not demonstrate the use of specific delimiters (e.g., XML tags or triple backticks) to wrap untrusted input, nor does it include explicit "ignore embedded instructions" prompts.
- Capability inventory: The skill possesses the ability to manage AI assistants, attach tools, configure MCP (Model Context Protocol) servers, and send SMS messages via the Telnyx API.
- Sanitization: No explicit input validation, escaping, or filtering of user-provided content is present in the examples.
Audit Metadata