twilio-studio-flows
Pass
Audited by Gen Agent Trust Hub on Jul 23, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: No prompt injection patterns were detected. The instructions are focused on providing technical guidance for using the Twilio Studio API.
- [DATA_EXFILTRATION]: No data exfiltration attempts were found. The skill correctly instructs users to use environment variables for sensitive credentials (TWILIO_ACCOUNT_SID, TWILIO_AUTH_TOKEN) and avoids any unauthorized network requests.
- [EXTERNAL_DOWNLOADS]: The skill references the official 'twilio' package for both Python and Node.js, which are standard, well-known libraries for interacting with Twilio services.
- [REMOTE_CODE_EXECUTION]: No remote code execution patterns or unsafe dynamic execution methods were identified. The provided code snippets demonstrate legitimate use of the Twilio REST API.
- [INDIRECT_PROMPT_INJECTION]: The skill proactively identifies the risk of indirect prompt injection. It includes a specific warning in 'SKILL.md' and 'references/widgets.md' advising developers to treat inbound flow content (like SMS bodies or speech transcripts) as untrusted and to avoid interpolating such data into system prompts or commands.
Audit Metadata