twilio-communications

Pass

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill implements webhook handlers (incoming_sms, whatsapp_webhook) that ingest text content from external, untrusted sources (SMS and WhatsApp recipients).
  • Ingestion points: request.form.get("Body") in SKILL.md.
  • Boundary markers: None identified; the instructions do not implement specific delimiters for external content.
  • Capability inventory: The skill has the ability to send messages, make outbound calls, and record audio via the Twilio API.
  • Sanitization: No explicit sanitization or instruction-filtering is applied to the incoming message body before processing.
  • [COMMAND_EXECUTION]: The skill uses the Twilio Python library to interact with external APIs and sets up a Flask server to handle incoming requests, involving potential command-like interactions with the Twilio platform.
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the twilio and flask Python packages to function, which are standard third-party dependencies.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 08:27 AM
Security Audit — agent-trust-hub — twilio-communications