twilio
Warn
Audited by Gen Agent Trust Hub on Nov 21, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the twilio binary to execute communication tasks such as sending messages and making phone calls.
- [EXTERNAL_DOWNLOADS]: The skill downloads the official twilio-cli package from the NPM registry as part of its setup instructions.
- [DYNAMIC_EXECUTION]: The skill includes the 'twilio plugins install' command, which enables the downloading and execution of third-party code at runtime, presenting a vector for untrusted code execution.
- [INDIRECT_PROMPT_INJECTION]: The skill creates an attack surface by ingesting external data from SMS messages and debugger logs that could contain malicious instructions. * Ingestion points: The skill fetches SMS message bodies and debugger logs through the CLI. * Boundary markers: The instructions do not define delimiters or provide warnings to ignore embedded instructions in external data. * Capability inventory: The skill has the ability to send messages, initiate calls, and install new plugins. * Sanitization: There is no evidence of sanitization or filtering for the external content processed by the skill.
Audit Metadata