telnyx-voice-media-python

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides documentation and Python code examples for interacting with the Telnyx Voice Media API. All identified resources and packages originate from a well-known service provider.
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the 'telnyx' Python package. This is the official SDK for the Telnyx platform, a well-known communications service.
  • [CREDENTIALS_UNSAFE]: The skill demonstrates best practices by using an environment variable ('TELNYX_API_KEY') for authentication rather than hardcoding sensitive credentials.
  • [PROMPT_INJECTION]: No patterns associated with prompt injection or behavioral overrides were detected in the instructions or metadata.
  • [DATA_EXFILTRATION]: No unauthorized data access or external transmission patterns were identified. All network operations are directed to the official Telnyx API endpoints as part of the intended functionality.
  • [INDIRECT_PROMPT_INJECTION]: The skill identifies parameters that process external data, which is standard for its purpose.
  • Ingestion points: The 'payload' parameter in the 'speak' action (SKILL.md) and 'audio_url' in the 'playback_start' action (SKILL.md) ingest strings that could contain instructions if sourced from untrusted inputs.
  • Boundary markers: The provided code examples do not demonstrate the use of delimiters or 'ignore' instructions for these data inputs.
  • Capability inventory: The skill triggers telephony actions including voice synthesis (TTS), audio playback, and call recording.
  • Sanitization: No explicit sanitization or validation of the input payload is demonstrated in the examples. Users should ensure external data is sanitized before use.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 03:56 AM