twilio-conversation-orchestrator
Pass
Audited by Gen Agent Trust Hub on May 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides purely instructional content and technical documentation for Twilio services. No malicious code or instructions were identified across the analyzed files.
- [CREDENTIALS_UNSAFE]: JavaScript and Python code examples correctly utilize environment variables for Twilio Account SIDs and Auth Tokens. There are no hardcoded secrets or instructions to store credentials insecurely.
- [EXTERNAL_DOWNLOADS]: Network requests in the documentation target official Twilio API endpoints (e.g., conversations.twilio.com). These are trusted vendor resources and do not represent a security risk.
- [COMMAND_EXECUTION]: The skill does not contain any shell commands or scripts that perform dangerous system-level operations or privilege escalation.
- [PROMPT_INJECTION]: The content is focused on API configuration and functional use cases. It does not include instructions intended to override agent behavior, bypass safety protocols, or leak system prompts.
Audit Metadata