twilio-rcs-messaging
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill includes instructions for installing the official Twilio SDK using standard package managers (
pip install twilio,npm install twilio). These are expected setup steps for the service and target the vendor's verified libraries. - [INDIRECT_PROMPT_INJECTION]: The skill provides code templates for sending messages where the recipient and content are dynamically determined, which could be exploited if the agent processes untrusted external data without additional verification.
- Ingestion points: The
to,body, andcontent_variablesparameters in the Python and Node.js examples withinSKILL.md. - Boundary markers: The examples demonstrate direct variable interpolation without explicit delimiters or instructions to ignore potential commands within the data.
- Capability inventory: The skill enables message transmission via the Twilio API (
client.messages.create), which is a network-capable action. - Sanitization: The documentation focuses on functionality and does not include logic for sanitizing or validating the input data before it is sent.
- [SAFE]: The skill recommends storing
TWILIO_ACCOUNT_SIDandTWILIO_AUTH_TOKENin environment variables rather than hardcoding them, which is the correct approach for secret management. All documentation links and API references target the official Twilio infrastructure.
Audit Metadata