Twilio SMS Automation
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of instructional content, configuration schemas, and code examples for Twilio integration. No malicious code, obfuscation, or unauthorized network operations were found.
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the processing of incoming SMS messages, which creates a potential surface for indirect prompt injection. This is an inherent risk of the skill's primary function (two-way messaging) and is managed through the agent's internal safety guardrails.
- Ingestion points: Incoming SMS message content processed via the
/sms/incomingwebhook example in SKILL.md. - Boundary markers: Not specified in the documentation examples.
- Capability inventory: Includes tools for sending SMS, making voice calls, and phone number lookups.
- Sanitization: Examples demonstrate simple string comparison for command handling; developers should implement robust input validation.
Audit Metadata