telnyx-ai-assistants-go

Pass

Audited by Gen Agent Trust Hub on Mar 27, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the official Telnyx Go SDK from the author's GitHub repository (github.com/team-telnyx/telnyx-go) to enable interaction with Telnyx services.
  • [CREDENTIALS_UNSAFE]: The skill demonstrates secure secret management by instructing the use of environment variables (os.Getenv("TELNYX_API_KEY")) rather than hardcoding credentials in the source code.
  • [COMMAND_EXECUTION]: The skill provides standard Go code examples for initializing an API client and performing resource management tasks (create, update, delete) via the Telnyx platform.
  • [PROMPT_INJECTION]: The skill facilitates the creation and execution of AI assistants that process untrusted data (e.g., the 'Content' parameter in the Chat method), presenting a surface for indirect prompt injection common to AI service integrations.
  • Ingestion points: External data enters through parameters like 'Content', 'Instructions', and 'Rubric' in various AIAssistant methods in SKILL.md.
  • Boundary markers: None provided in the implementation examples.
  • Capability inventory: The skill allows network communication with Telnyx's AI APIs and can trigger manual test runs or imports from external providers.
  • Sanitization: No explicit sanitization or filtering is documented for the data passed to the assistant parameters.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 27, 2026, 01:16 AM
Security Audit — agent-trust-hub — telnyx-ai-assistants-go