twilio-communications

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted external data which creates a surface for indirect prompt injection.
  • Ingestion points: The body parameter in the send_sms method and the Digits parameter in the menu_selection route (SKILL.md).
  • Boundary markers: There are no explicit delimiters or instructions provided in the templates to differentiate user-provided content from system instructions.
  • Capability inventory: The skill utilizes the Twilio REST API for network-based communication tasks including sending messages and managing voice calls.
  • Sanitization: The skill performs format validation for phone numbers and matches IVR digits against allowed values, but does not sanitize the contents of SMS message bodies.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 01:15 AM