telnyx-texml-python

Pass

Audited by Gen Agent Trust Hub on May 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or security risks were detected in the skill instructions or code snippets.
  • [EXTERNAL_DOWNLOADS]: Recommends installing the 'telnyx' package via pip. This is the official SDK from the vendor and is considered a safe and standard dependency.
  • [COMMAND_EXECUTION]: Provides a shell command to install the required library ('pip install telnyx').
  • [CREDENTIALS_UNSAFE]: Encourages the secure practice of retrieving the API key from environment variables ('os.environ.get("TELNYX_API_KEY")') instead of hardcoding it.
  • [SAFE]: (Indirect Prompt Injection Surface) The skill defines methods that ingest external data such as phone numbers and message text. 1. Ingestion points: Arguments like 'to', 'from_', 'text', and 'voice_url' in 'SKILL.md'. 2. Boundary markers: None present in the snippets. 3. Capability inventory: Network operations via Telnyx API calls. 4. Sanitization: Not explicitly implemented in the provided documentation examples.
Audit Metadata
Risk Level
SAFE
Analyzed
May 13, 2026, 04:20 PM
Security Audit — agent-trust-hub — telnyx-texml-python