twilio-voice-outbound-calls
Pass
Audited by Gen Agent Trust Hub on Jun 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security vulnerabilities were detected. The skill provides legitimate guidance for integrating with a well-known service.
- [EXTERNAL_DOWNLOADS]: The skill references official Twilio SDKs available through standard package registries (npm and PyPI). These are trusted libraries from a well-known service provider.
- [COMMAND_EXECUTION]: Includes standard commands for dependency installation (
pip install twilio,npm install twilio) and environment setup. - [PROMPT_INJECTION]: The skill includes instructions that process external data (phone numbers and TwiML). It mitigates potential indirect prompt injection risks by explicitly instructing the agent to confirm the recipient and intent with the user before placing irreversible calls.
Audit Metadata