send-text-message
Warn
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
orthcommand-line tool to interact with the Textbelt API. The command template provided in Step 2 (orth run textbelt /text --body '...') directly interpolates the user-provided<phone_number>and<message_text>into a shell string. This creates a command injection vulnerability if the message contains single quotes or other shell-terminating characters that could allow an attacker to execute arbitrary commands on the agent's host system. - [DATA_EXFILTRATION]: The skill's primary function is to transmit user-supplied data (phone numbers and message content) to an external API (Textbelt). While this is the documented purpose, it constitutes data leaving the local environment to a third-party service.
- [COMMAND_EXECUTION]: Step 3 uses dynamic command construction (
/status/{textId}) to check delivery status, which relies on thetextIdreturned from a previous shell command execution.
Audit Metadata