twilio-communications
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill implements patterns that process external data through SMS and voice channels, creating an attack surface for indirect prompt injection.
- Ingestion points: The skill accepts phone numbers and message bodies in the
send_smsandsend_verificationmethods, and processes keypad input via themenu_selectionwebhook (SKILL.md). - Boundary markers: There are no explicit delimiters or specific instructions provided to the agent to ignore potentially malicious content embedded within the message bodies or inputs.
- Capability inventory: The skill possesses the capability to send SMS messages and initiate voice calls using the Twilio SDK (SKILL.md).
- Sanitization: The implementation includes a
validate_e164method to enforce phone number formatting and uses Twilio'sRequestValidatorto ensure the integrity of incoming webhook requests (SKILL.md).
Audit Metadata