telnyx-ai-assistants-ruby
Pass
Audited by Gen Agent Trust Hub on Mar 26, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The documentation recommends installing the official
telnyxRuby gem from the public registry, which is the expected dependency for this service. - [CREDENTIALS_UNSAFE]: Examples demonstrate secure credential management by fetching the Telnyx API key from environment variables instead of hardcoding it.
- [PROMPT_INJECTION]: The skill provides an interface for AI assistants to process untrusted data, creating an attack surface for indirect prompt injection. 1. Ingestion points: Untrusted content is ingested via the
contentparameter in the chat method and theinstructionsfield during assistant creation (SKILL.md). 2. Boundary markers: The provided examples do not implement delimiters or specific instructions to ignore embedded commands in user input. 3. Capability inventory: The skill performs network operations to the Telnyx API and can be configured to connect to external MCP servers via URL. 4. Sanitization: There is no evidence of input validation or sanitization being performed on user-provided content before it is processed by the AI models.
Audit Metadata