twilio-communications
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill handles untrusted user data for messaging capabilities.
- Ingestion points: The 'body' and 'to' arguments in the 'send_sms' and 'send_verification' methods.
- Boundary markers: None; message content is passed directly to the API without delimiters.
- Capability inventory: Messaging and voice call initiation via the 'twilio' Python library.
- Sanitization: Implements E.164 phone number validation; no content filtering is performed on the message body.
- [Data Exposure & Exfiltration] (SAFE): Twilio credentials (SID and Auth Token) are securely retrieved from environment variables rather than being hardcoded.
- [Command Execution] (SAFE): No evidence of unsafe command execution or shell spawning using user-controlled inputs.
Audit Metadata